Photo 365 2026. Year 5, Month 5. Photo-a-day for the month of May 2026.

The post May 2026 | Photo 365 appeared first on thejaymo.net.

Daily Averages

It’s Tuesday afternoon I’ve been into Central London and back. I got half drowned in a storm, it was glorious sunshine, and now it’s apocalyptic rain and thunder again? Always.

Back in 2020 I wrote about how I use my RSS reader. And that is, still. The main way i consume the Internet. But I mostly now use it on my phone, in conjunction with raindrop.io. Ive almost entirely replaced social media consumption with article reading and … talking to the AI that lives in my bookmarks lol.

Anyways, I direct you to that 2020 post, as in it I shared some of the daily average stats from my ‘webtime tracker’ extension that I had installed into my web browsers during the early lock down to try and get a grip on my attention with some hard metrics and data.

I wish I had a screenshot of the whole top 10 but I did share some snippets of the metrics in that old post.

I was spending nearly 26 min on twitter a day in the deep of the pandemic.

I’ve still have the app installed, and 6 years later here’s my total daily averages over the last 6 years.

*interesting*

I note that this tracker data is from the extension installed on my personal chrome profile rather than the one I use for work. So this is representative of where I spend my “free time” when i’m looking at my browser for fun, and not for money.

Anyways. On a whim, I just downloaded the full data set from the extension as JSON and had my pal Claude rustle me up a ‘bar race’ animation in about 3 mins. So here’s the last 6 years of daily averages / websites that I spend time on ‘for fun’ month by month.

I can see in the animation when iIstoped using google docs for my diary and moved to Day One, and then see a further reduction when I moved all my writing offline to Obsidian + iA writer and more recently, my own vibe coded word processor.

The other observation is that over the last few years I’ve consumed way too much Youtube!!?? I blame people like Noah Caldwell-Gervais, and Fimdeg’s 7.5 hour long oral history of the making of Morrowind lol. I love just sticking on a long form things and doing other things around the house, but the clock still clicks on.

On The Blog

AI-Generated Interfaces and the Delamination of Application UI

As AI separates the UI from the application layer, liquid interfaces point towards the next era of software design.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

The Ministry Of My Own Labour

• Edited and exported a new episode of Experience.Computer. Out Tuesday
• Sorted out some financial stuff
• Removed nearly 6k words from the next episode of permanently moved draft script lol
• Two calls.
• Got sent a draft of a piece by a friend. I slung it on my kindle
• Lots of reading to do.

Terminal Access

Sarah Friend posted a great piece today on “What Kind of Clock is an LLM? — All computational systems contain a model of time and all of them are wrong.”

It’s so good you should deffo read it.

Once a day maybe, the laptop calls out to an NTP (Network Time Protocol) server to reorient. In between calls, it can drift. On a more machinic scale, it makes no guarantees about task processing. If that laptop were to be for example, controlling a CNC bit spinning at 3000 RPM cutting through a piece of sheet metal, or stabilizing a drone while accepting the navigational commands of a distant pilot, it would stutter. If a rogue process, maybe a defrag or cleanup task took over the CPU, the bit would slow imperceptibly, and the cut would be too short. Somewhere, a drone falls out of the sky.

Reading

I finished Hive by Dan Abnett. Like i said last week, I feel like he had a story to tell and was exhausted by the work he’s done in the wider setting and needed a change. Also there’s a part of me that feels like it was written with a bunch of side eye towards Adrian Tchaikovsky now also playing in the 40k universe.

I also *finally* finished Impromptu Man: J.L. Moreno and the Origins of Psychodrama, Encounter Culture, and the Social Network. A really fantastic biography of one of the most important psychotherapists of the 20th C who has, largely, been written out of history. Basically everyone you know was influenced by him.

EXUM – In Russia. A is 9 (LP)

I’ve been really into this super delicate album this week. It’s an eclectic experimental mix of strings, noise, sound art, melodic vocals. All sorts of things really. To just list all those things however doesn’t really do it justice. Looking at the reviews, its quote polarising but I think Its just wonderful.

Remember Kids:

The post Daily Averages | Weeknotes #441 appeared first on thejaymo.net.

Towards the end of my post back in march about the near future of agents I mentioned possible changes to the architecture of how Application and UI interact.

Once that hard layer is built into applications and websites, something happens to the way software operates. The UI stops being the only control layer, and becomes the human layer only. The app and the interface become completely divorced.

This idea has basically been the working hypothesis across a number of the group chats I’m in for at least the last year. Over time I’ve been exposed to a great deal of manic experimentation and discussion about this trajectory from some of the best designers I know.

The clearest signs however that the UX layer is actually delaminating from the application layer came this week at Google I/O with their announcement of Gemini 3.5 Flash-powered Google Search results. In real time, an agent will wake up inside of Google’s code-harness software Antigravity, and dynamically build an interactive page of search results similar to the hypertext objects I describe here. You can see the process demonstrated in the keynote below, I’ve queued it up:

Google has been gesturing at dynamic interface generation since the original Bard era; but the most recent I/O made it feel like a real product direction. I’ll also note, that prompting the search box to give you 10 blue links is *exactly* the kind use case that Google want you to use it for!

There are a whole bunch of terms being used describe these kind of dynamic front ends right now, I like On-the-Fly UI (OTFUI), but I’ve also heard: Liquid UI, Disposable Interfaces and Runtime Artefacts used in conversation as well.

The Great Delamination

Another place you can see this kind of Liquid UI/UX emerging is on dedicated AI hardware that has a fairly constrained action dictionary. For example, the much maligned Rabbit R1 recently got a massive software update to Rabbit OS 2, and it lets you vibe code apps using text to speech:

Matt Webb is also exploring drag and drop / dynamic UX and software interfaces for AI hardware too at his most recent venture.

Another example can be seen from Manuel Odendahl in this this video where he demos “disposable software“, inspired by Apple’s original HyperCard:

And my friend Ramon Marc has been been exploring dynamic front end interaction patterns for non technical users recently and came up with this last week:

It’s an imagined middleware layer that takes a short intent from the user as a text input, and “Double Diamonds” the idea: exploring what would / could be possible from the limited prompt and then constrains it back down to a set of options and questions to show back to the user to clarify / select and confirm before it generates the actual app.

I kept iterating on unfolding intent to see how it could feel in more practical flows, so this is an evolution of [[sxk4bapy|folding intent]].I kept iterating on unfolding intent to see how it could feel in more practical flows, so this is an evolution of folding intent. The core idea stays the same: a prompt is an intent. It gets translated into a function ([[30bptv1y|inspired by Agentic Algebra]]), which produces a JSON tree, where each leaf is a UI paradigm for more granular user input. I kind of think we’re getting into territory where we can make more contextual, hard interfaces with this. Think: I want pizza from place xyz takes the intent, pulls context from the pizza place, and builds a UI based on the tree and availability.

There is another iteration here, that walks though the intent and surfaces the permissions for the user to grant before execution. Based on the principles of hardness. The goal being that vibe coding liquid UI apps is made simple to users who don’t know anything about coding at all. (more on this further down the post)

So… if UX is going to delaminate from applications, one of the things we need to think about is the speed at which these front ends can be conjured into existence by the bot. In RM’s demo video, you can see the token counter coming in at around 60 tokens per second (tok/s) and the UI taking 22 seconds to generate.

Google’s new Gemini 3.5 Flash model comes in at around 300 tokens a second depending on connection time and latency so if at 60 tok/s, RM’s demo takes 22 seconds, At 300 tok/s, the same token budget takes about 4.4 seconds. But during the Google I/O keynote, they showed off an internal Gemini model running at 1,500 Tok/s. Which is 25× faster! Using the same example this becomes 0.8 seconds. Essentially meaning the UI generation becomes instantaneous.

Iron Speciation Triangle

Given this seems to be an observable trend, I’m pretty sure this is the direction of travel. So we should probably take a step back, and zoom out, to talk about model development in general.

Years ago now, I wrote about “maximal intelligence at all levels”. Local models, cloud models, frontier models, etc, will all speak to one and shunt tasks up and down depending on capability and speed requirement.

General-purpose models like Claude Mythos, the next ChatGPT and Gemini models, are all going to carry on getting better as they have been. I think however, over the coming months, and definitely in the next 18 months or so, we are going to see a speciation of AI models.

We already see the first signs of this with the difference between thinking models and instant models, and also in the open source world where small and extremely performant coding models are being developed. But these are only the embryonic versions of the coming split. There is a lot of headroom to be found by keeping intelligence roughly steady while pushing speed, cost, latency, and availability into completely different regimes. It seems obvious and logical that the major labs will go further than they already are, and will produce different models specialised for different tasks alongside their general purpose build-the-machine-god frontier models.

Imagine for a moment that this time next year there’s a model that isn’t appreciably more ‘intelligent’ than the one you are using today. But it’s extremely cheap, and very fast. As fast, if not faster, than the 1,500 Tok/s model we know Google already have internally.

If we take the classic iron triangle of quality, speed, and cost, but for our purposes we’ll use intelligence for quality. We can pick two and work our way around the triangle to speculate on three distinct future species of machine mind:

• Fast and Intelligent, but not Cheap: These already exist in a way, with both Anthropic and ChatGPT offering ‘fast modes’. These will get used for real-time agents, and developers in high-stakes coding environments. But also high-frequency trading, and tasks that require extremely performant multimodal interaction: robotics, security applications, and even surgery in healthcare. Maybe they are dispatched by general models with a one-off agentic task. They are really fast and intelligent, but you just burn money using them.
• Cheap and Intelligent, but not Fast: This is the kind of use case that we are seeing emerge with Claude’s new “dreaming mode”—batch minds that can be left to run overnight, reading things, doing background memory-consolidation, auditing codebases, simulating and generating reports, planning, and doing deep research. Useful for the kinds of jobs and applications that you don’t necessarily need to run in real time. Tasks that you can wait on.
• Fast and Cheap, but not Maximally Intelligent: This is the baseline model I’ve already explained being used for instantaneous UI generation.

All three of these model species would of course, require vastly different architectures at the data centre level: hardware and memory optimisations, and so on. Also important to note, as a lot of people miss this: The literal, physical substrate that LLMs run on evolves and changes to meet the needs of the software design of the model. These kinds of model species will emerge as more data centres get finished up and more compute becomes available.

Runtime Sovereignty

Beyond the data centre, we also have to consider the emerging ASIC chips for AI, where models are essentially baked onto the chip. Taalas recently entombed Meta’s old Llama 3.1 8B in silicon and achieved speeds of nearly 17,000 tok/s. If a chip like that were running a model intelligent enough to execute the example above, which Llama 3.1 8B is not, the same operation would take about 78 milliseconds or 0.07764706 seconds. 283.3× faster than RM’s demo experiment.

Whilst these kinds of fixed chips can’t be updated or changed, if we end up in the near future with “good enough” intelligence running locally, and insanely fast, then these kinds of Liquid UIs might end up being generated on the edge by the hardware/physical interface. Sort of similar to what I was thinking about when I first wrote about Helpful LLocal Models last year.

If we get this kind of local improvement then the iron triangle becomes a square and sovereignty becomes a new variable. Local actions won’t necessarily be performed by the smartest minds, but they do live on your laptop or phone and are optimised for latency, privacy, persistence, and ownership etc.

In addition to open source coding models, you can already see other kinds of specialised models tuned for speed and subject matter starting to emerge. OpenMed, a terminal-native clinical agent explicitly engineered around strict local compliance, and data sovereignty. Using MLX it clocks 24–33× speedup on standard Apple Silicon for local privacy filtering. OpenMed is a real breakthrough showing that a clinical AI can now live entirely inside hardware that a small local clinic can actually own, inspect, and govern. Note: these things can run on iPhones and iPads too at very usable speeds.

As the capabilities of local models increase, we’ll see all sorts of new agent types emerge, ones that run tasks as batch processes overnight. Very similar to the way that the iPhone has run its machine learning over your photo library for the last decade. Local models will be able to tag, process, read, and summarise all your local files, photos, and documents on the device and produce embeddings for them. Imagine being able to search Spotlight for “recent invoices from X” or “that spreadsheet about Y”.

In a maximal-intelligence-at-all-levels world, the winner wins by proximity

Constitutional Software

With liquid runtime artefacts, the question becomes: who is allowed to generate them, where, with what data, under what rules, and on whose behalf? This is of course a question of governance.

Once interfaces are generated on demand, and actions are distributed between cloud models, local models, specialist models, and device-level agents, the interface is no longer the boundary of the application. It’s a membrane between user intent, available context, permissions, model capability, and machine speed. All of this will require a great deal of what I call hardness.

“What can this software do?” becomes: “what is this software allowed to do?” Which model is allowed to see which data? Which actions must stay local? Which decisions require explicit permission? Which agents can speak to each other? Which layer gets to say no?

It’s all very complicated and will need a lot of governance. In the group chat Rafa has been calling this design space constitutional software.

What rules or protocols govern the generation of the UI. Which screens, tools, agents, and actions may appear and under what circumstances. There is a great deal of future work required if it’s going to become bullet proof.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

The post AI-Generated Interfaces and the Delamination of Application UI appeared first on thejaymo.net.

Telephone

I found out this week that the information passing parlour game “Chinese Whispers” as it was called when I was growing up (“Telephone” in the USA) isn’t some super old English name for it. It’s a relatively recent term first used in print in 1964! Drawing on racist stereotypes about how Chinese people must all be communists and whispering secrets and speaking in a way that was deliberately confusing to Westerners.

Before that, Victorians called it “Russian Scandal” (1861) and “Russian Gossip” (1880s). An even older 16th-century Italian precursor was the “game of the ear.” Ironically, in China, the game is just called chuánhuà (传话) “passing words.”

Whilst game of the ear is the oldest written name/evidence we have for the existence of the game, it seems to me that the phenomenon of oral transmission mutating from person to person must be tens’s if not hundreds of thousands of years old? Sitting around a campfire and passing a narrative around the group from ear to ear is something we could and would have done for the history of humanity. ‘Gossip’ is a much better metaphor and name than telephone or whispers.

Later on in my wikipedia binge I found this cool PDF from 1945 from the New York Academy of Sciences (NYAS) a lecture by Gordon W. Allport and Leo J. Postman on The basic psychology of rumour. They say that rumours arise when highly important events are shrouded in ambiguity, a combination that thrives during periods of high societal censorship an shock events like Pearl Harbor.

They classify rumours into three broad categories: “fear,” “hostility,” and “wish”. Each providing a dual psychological function: explaining away personal anxiety and providing people an emotional outlet to vent anger at convenient scapegoats, like minority groups or the government. To understand how rumors distort reality, the authors conducted experiments showing that stories undergo a three-part “embedding process” as they spread: leveling, sharpening, and assimilation. 

• Levelling strips the story of most details to make it concise and easy to remember.
• Sharpening selectively exaggerates a few specific, often emotionally charged details that stand out.
• Assimilation reshapes the remaining facts to fit the listener’s pre-existing cultural stereotypes, prejudices, and expectations.

in the end, the objective truth is completely replaced by a subjective narrative that reflects the group’s collective anxieties and biases, meaning that by the time a rumour has traveled through a chain of people, it is no longer a valid guide for belief or action.

I’ve been thinking a lot about this with regard to the neo-oral, or post-truth condition. The authors of the paper never envision the world we are in today. When fact checking, and verifiable sources of information are themselves subject to the same distrust and ambiguity pressures that cause the rise in rumour/conspiracy etc in the first place. If you can’t rely on external “secure standards” as they call them, instead you have to lean on internal and social safeguards that the authors didn’t fully anticipate or explore but are logically implied in the text. Rumours (conspiracy) are, to use Postman and Allport’s words a “barometer of social strain.”

If you work in media today, you need to understand this: if a meme or rumor goes wildly viral, the rumor itself is the truth about the underlying fear, even if the facts are totally wrong. You cannot fight an emotional rumour with a spreadsheet of facts. You have to address the anxiety behind it. Which is the exact opposite of the institutional fact checking industry like BBC verify are trying to do. Because “Feelings don’t care about facts”.

But institutions face massive pressure to manufacture optimism. If millions of people feel like their country is sliding backward, and an outlet like the BBC refuses to validate that reality, the broadcaster becomes part of the “ambiguity” fueling the conspiracy in the first place. Admitting that we are in deep trouble is dismissed as unpatriotic or “doomerism.”

But we don’t need manufactured hope; we need a return to emotional truth. Which is something I’ve been thinking a lot about recently with solarpunk. Luckily, emotional truth, rather than fact is exact the sort of thing thing the Arts and Humanities do best.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

Terminal Access

This is pretty cool. The entire catchment of the River Wye has become the first in the UK to be formally granted legal rights as a living ecosystem through a new charter.

While much of the Wye, or Gwy in Welsh, is protected as a special area of conservation, and the rights in the charter are already recognised across existing legislation and regulatory frameworks, the river has suffered near ecological collapse over the past decade.

Campaigners say excess nutrients from the rapid expansion of industrial chicken farming in the river’s catchment area – aggravated by sewage spills – have caused algae, fungus and weed growth that has suffocated the ecosystem.

Reading

I finished reading Super Nintendo: How One Japanese Company Helped the World Have Fun by Keza MacDonald. It’s a really engaging history, and is told really well with a blend of personal anecdote/history and original interviews/reporting. A whole career’s worth of interivews make the history feel lived though. Highly recommend it!

I started reading Hive by Dan Abnett. It’s an absolutely mammoth two part Warhammer 40k novel. Super cool setting. Feels like he has a story to tell and was exhausted by the wider setting and needed a change in setting.

Castle Rat – The Bestiary (LP)

Now.. I’m a sucker for doom, stoner rock, and psychedelic metal band. Especially if they dress in 70s hammer horror esq costumes and the whole thing is a concept album telling the story of mystical creatures preserved by “The Wizard”.

Commenting on the album, The Rat Queen states: “‘The Bestiary’ is a conceptual book of beasts… containing a collection of mystical creatures from a world forgotten. The last remaining souls of each have been gathered and preserved by ‘The Wizard.’ Cautionary tales of each beast and The Wizard himself are woven through the power of traditional heavy metal song and spell.”

This band RIPS!!

Remember Kids:

The post Telephone | Weeknotes #440 appeared first on thejaymo.net.

Just Sad

It has frankly, been a shit week. My friend Gordon White died.

A loss of a force and a friendship that has been consistent for a quarter of my life. I have so much to say, but can’t find the words just now. Just sad.

Grief is a process that has only a beginning, so I am trying not to mistake this first darkness for the whole sky.

My heart goes out to James, his family, and friends x

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

Reading

Still reading Super Nintendo: How One Japanese Company Helped the World Have Fun by Keza MacDonald. It’s very engaging drawing on a careers worth of 1-2-1 interviews and archival reporting.

Parlour Greens – Emeralds (LP)

Soul/jazz/funk super group Parlour Greens have a new album out and damn…. the pocket on this album is craze. Funky as hell.

Remember Kids:

The post Just Sad | Weeknotes #439 appeared first on thejaymo.net.

Jubensha Con

On Saturday I went to Jubensha Con 2026. The first english language convention about the Chinese social phenomenon of Jubensha.

We’re the world’s first convention dedicated to English-language jubensha. Jubensha is a phenomenally popular “scripted murder” format of games originating in China, where participants roleplay as detectives and/or suspects in mystery to deduce who the culprit is. In recent years it’s broadened far beyond murders into investigations of all kinds, and is spreading internationally.

We’re organising this convention to give people a chance to try out games, spur new collaborations, and help grow the scene. It’s a deliberately lo-fi, informal, and non-profit endeavour, and we want to keep costs as low as possible so money isn’t a barrier to entry.

Huge shout out to Adrian Hon and all the other organisers of the event. I had an amazing time there.

If you are unfamiliar with it as a form, this 2024 People Make Games documentary about it is a good place to start.

I haven’t written up my notes properly from Saturday’s talk track yet, but the following brain dump represents most of the big takeaways, and will forms the basis for them.

• China has/had no extant consumer market for LARP/TTRPGs/Murder Mystery/Escape Room/dinner theatre/or Euro style boardgames. No do young people have a huge ‘Party’ culture. As in having a party. So when Jubensha came along and combining elements from all those things around a social deduction mechanic it exploded in popularity and immidiatly fused with the dating market.
• Jubensha is treated more like a social commodity which is why there was such a boom/bust explosion in Jubensha. Its more like going to Karaoke than something involving a trained and talented performer as the DM. Because of this profit margins are tight, and quality of massively variable. Necessitating the creation of and App called Qiandao to keep track of and rate games and parlours providing them.
• Despite the boom and bust cycle post pandemic the industry is still worth $2billion.
• Yulin Tian and Yihan(Clytze) Li talk on Scripted Intimacy: Designing Emotional Experience in Chinese Jubensha Games was very interesting. A great deal of the current trends in the games have moved away from murder mystery and towards deeper emotional play. Instead of all 6 couples/players being equal in the game. In Script games, there is a clear Main Character and supporting cast. Some MC players will pay their friends to sit though 6-8 (even 13 hour long games) so they can experience them.
  • I think it’s interesting that the new form of script games treat Jubensha as a social technology. Mechanisms like: archetypal casting, asymmetric character scripts, scripted physical moments like weddings and symbolic gift-giving, are essentially techniques from therapeutic and theatrical traditions, packaged into a consumer product. VERY Interesting design space.
• Eastern Jubensha has points systems and defined winners; Western adaptations are moving away from overt win conditions towards pure storytelling. Which seems to reflect a deeper philosophical split about what games are for. The Western instinct is that competition undermines roleplay but in China, the instinct seems to be that stakes require scorekeeping. Neither is obviously wrong, and the tension between them is a productive design question.
• All Jubensha games require a lot of reading, upfront and during play. But Chinese players read Jubensha scripts faster because Chinese is a logographic language, meaning more information is compressed per character. Western designers face a genuine cognitive-load problem that their Chinese counterparts simply don’t. The proclivity toward reading and comprehension etc shapes how dense and long english scripts can realistically be.
• There was an observation that game authors/designers in China have no creative community per say, and games are judged solely by market profitability, and this is was put as an example of when a creative medium scales too fast without building the infrastructure that sustains quality.
• Eastern jubensha is frequently designed for exactly 3 male and 3 female players, with storylines to match, often with a romantic or dating dimension built in. This is a design norm, but for a Western audience steeped in inclusive design, this is genuinely startling.
• In the UK due to the lack of parlours and places to play fully costumed Jubensha, boxed games without a DM seem to be the emerging form factor and design space for play.
• In the West the DM in TTRPGs are co-players in the game. With a level of social respect that Jubensha DM’s working in parlours / treated like Karaoke spots don’t get.
• Lastly, many of the game authors and designers in China come out of the online fandom/fan fiction world. So many of the new emotional script games, their logics and archetypes can be esiely classified by existing online fandom community nomenclature.

Super cool day out!

On The Blog

April 2026 | Photo 365

Photo 365 2026. Year 5, Month 4. Photo-a-day for the month of April 2026.

SSRZ15: Monsters in the Mirror

This zine contains the full essay transcript alongside an introduction and afterword written exclusively for print, material that doesn’t exist in the audio. 36 pages. A5.

Buy on Etsy

Properly printed on heavy stock with thick covers. Hand stamped twice, copy number and FOG logo. This is remaining stock after the print run for my paid subscribers. Once they’re gone, they’re are gone. £18 + shipping worldwide

CAVEAT EMPTOR: International zines are posted with full customs declarations as printed booklets. Depending on your country, local VAT, customs, or handling fees may be due on arrival.

Photo 365

The Ministry Of My Own Labour

• Call with the WineDark crew
• Finished end to end draft of INTERNET OPERATOR episode 303
• Wrote a first draft of ‘ON THE CONSTITUTION OF THE MACHINE MIND’
• Started editing SLOP MACHINES
• Worked on a job application
• Did some work spreadsheeting for a company I advise
• Did a days work over the week working on a set of MCP/REST api prompts for a SME.

Terminal Access

Andrew Dana Hudson’s debut novel Absence is now out!

I was lucky enough to read this in several drafts including the opening, when he thought it was going to be a novella 😂. Its a great story, really gripping and has a lot of philosophical reflection throughout . If you like authors like Kazuo Ishiguro then I think you’ll enjoy Absence! ADH has put the opening chapter up online if you want to whet your whistle.

You can get this book wherever books or ebooks are sold! Find it on Amazon, B&N, Bookshop.org, or ask your local bookstore to order you a copy.

There’s also an audiobook edition (Audible, Apple Books, Kobo), and — based on my own listening as well as the reviews flooding in at Goodreads — the narrator Dan John Miller does a great job.

Reading

I started listening, to AND FINISHED, all 30 hours of Strength of the Few . The second book in the mammoth Hierarchy trilogy by James Islington. It picks up directly from book #1 with no handholding. I can see why people are saying this set of books is fast becoming this decades most important fantasy series. What a book series. Amazing.

Moved on and now I’m listening to that Nintendo book thats in the hardback non-fiction charts at the front of Waterstones. Super Nintendo: How One Japanese Company Helped the World Have Fun by Keza MacDonald.

Chiminyo – NRG 5 (LP)

Chiminyo’s 2025 NRG4 album recorded live at Ronnie Scotts was a highlight of the year last year. Not just as an album, but as a beacon of whats going on in UK music right now. NRG 5 is no different. Recorded live at Peckham Levels, it captures the kind of cultural energy that’s instantly familier to anyone that’s recently spent time amidst London’s concrete spaces.

I mean honestly. What could be more London that this in 2026?

Remember Kids:

The post Jubensha Con | Weeknotes #438 appeared first on thejaymo.net.

Photo 365 2026. Year 5, Month 4. Photo-a-day for the month of April 2026.

The post April 2026 | Photo 365 appeared first on thejaymo.net.

Turnstones

I can’t belive its MAY. It feels like only yesterday that I got back from Sri Lanka. With every passing year, it feels like life is accelerating, but then again, so are events.

It’s Bank Holiday weekend here in the UK, so projects are on hold. The GF went to Scotland on Friday to see some friends for two nights, and rather than be on my Jack I went back down to The Chalk. I was only at home a couple of weeks ago for Easter, but in between then and now, my parents have been to Hong Kong and Taiwan and back to see my younger brother. So we had a lot to catch up on.

When I got back on Friday mum asked me what I wanted to do whilst I was home, and the two things I wanted to do were; sit on the beach in the sunshine and, go for a walk along a specific part of the coast. So we did both!

Very nice! Also saw some Ruddy Turnstone’s along the sea wall as the tide was coming in:

Today being bank holiday Monday, I’ve done a bunch of domestic things around the house. Once i’ve posted this I’m going to read my book with a cup of tea.

SSRZ15: Monsters in the Mirror

This zine contains the full essay transcript alongside an introduction and afterword written exclusively for print, material that doesn’t exist in the audio. 36 pages. A5.

Buy on Etsy

Properly printed on heavy stock with thick covers. Hand stamped twice, copy number and FOG logo. This is remaining stock after the print run for my paid subscribers. Once they’re gone, they’re are gone. £18 + shipping worldwide

CAVEAT EMPTOR: International zines are posted with full customs declarations as printed booklets. Depending on your country, local VAT, customs, or handling fees may be due on arrival.

Photo 365

The Ministry Of My Own Labour

• Drafted the spine / argument of the whole of Episode 303 of permanently moved. Just need to write it now.
• Had a long workshop/call about the idea of ‘industrial coordination arbitrage’. Meaning there’s a competitive advantage to re-engineering or figuring a potential customer (or competitor’s) AI model provider and the system prompts of the business. “I know I can sell to you better if I know your infra’s thinking patterns” Inspired by this article on how LLMs prefer to sniff their own farts

Terminal Access

Woke up this morning to a pingback from Tracy Durnell’s Mind Garden on this fantastically hypertext dense post: Aura through the Cult of Self: opportunity creates authenticity. It’s very much worth your time, i came away with a lot of thoughts and seeds of ideas.

In our modern, individualist culture, self-expression has become “not just a moral requirement, but a teleological one,” writes Tara Isabella Burton. “It is what we, as human beings, are for.” Rather than inheriting our identity from our roles in society as we did in the past, today we are each responsible for constructing our own identity. And so, writes Byung-Chul Han, “the production of self becomes a permanent activity.”

Importantly, we must construct our identity both for ourselves and for others. In On Photography, Susan Sontag explains that our culture believes that “images possess the qualities of real things,” but viewers apply this logic in reverse and “attribute to real things the qualities of an image.” Because of this interpretive transference, we can use images to create our selves online, irrespective of physical reality or ownership.

Reading

I’m reading Henryk Jurkowski’s Aspects of Puppet Theatre right now. This book is a ‘classic’ and is on most theatre and puppety syllabi. and i can see why. It’s so interesting! and is one of those books that has totally exploded my thinking into all different directions. No wonder it’s so influential

Still reading The Mirror of Simple Souls by Marguerite Porete. Alan Chapman told me to read it after a conversation last year, and now I’m beginning to understand why.

On the recommendation of a few friends, I’ve started Listening to Will Of The Many by James Islington. I’m about half way though… its not the book i was expecting… it’s very good, it’s just… had I read the blurb, I wouldn’t have read it.

Denonbu – Ultrarhythm (Single)

I have just discovered Japanese producers Denobu, who have a whole J/Hyper-pop transmedia thing going on. An anime world full of story and key characters combined with a the music side which involves dropping a new single every week on a Thursday. They have an enormous back catalogue and i’ve only scratched the surface so far, but this track is a banger.

Remember Kids:

The post Turnstones | Weeknotes #437 appeared first on thejaymo.net.

Nearly Doable

As you might have seen, Issue #15 of my zine went out to subscribers last week. I can honestly report that sending physical things to people is bloody brilliant. Big thanks to everyone who’s been in touch about it.

When I first started making the zine back during the pandemic, I had some hope that this might be the direction of travel. Making and self-publishing proper physical artefacts that are connected to online work and creative projects, then sending them to people in the post.

After a long slog with the initial years of the zine, and making the podcast weeky, I can feel that ambition starting to become real. The whole enterprise hasn’t been “easy”, it is now almost doable. I can see the shape of the new format and how it plays out

I have been thinking a lot about pace and form since finishing 301 last year. I just don’t think people should need to post their creative work online every week for forever. Longer, more considered things, especially when they have a physical component, seem to be a much better shape. Combined the audio episode and the zine are asking for a different kind of attention. They suit the culture I want to live inside of, so I’m doing my bit to help make it happen for others.

Anyway. If sixteen-year-old me, or nine-year-old me for that matter, knew that at the age of forty I’d have a zine shipping around the world, with a proper print run and subscribers waiting for it to arrive in the post, he would be over the moon.

Anyways, there are still a few remaining copies of Issue #15 available on my Etsy.

Buy SSRZ15: Monsters in the Mirror on Etsy

This zine contains the full essay transcript alongside an introduction and afterword written exclusively for print, material that doesn’t exist in the audio. 36 pages. A5. Properly printed on heavy stock with thick covers. Hand stamped twice, copy number and FOG logo.

This is remaining stock after the print run for my paid subscribers. Once they’re gone, they’re are gone.

£18 + shipping worldwide

Buy on Etsy

CAVEAT EMPTOR: International zines are posted with full customs declarations as printed booklets. Depending on your country, local VAT, customs, or handling fees may be due on arrival.

On The Blog

Raindrop.io Stella Prompts for Batch Processing Bookmarks

After a lot of trial and error with batch processing, I realised the best approach was to call Raindrop’s MCP tool names directly using the public API documentation.

So below I’m sharing two versions of the prompt I ended up with. This prompt uses my own Raindrop setup, including collection names like thejaymo, my preferred bookmark note style, and the rules I use for deciding what goes into my public links feed. You’ll need to swap in your own collection names, tag, and review criteria before using it yourself.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

The Ministry Of My Own Labour

• No work this week 😩 but I pushed a whole bunch of personal work and projects forward.
• Zine stuff obviously
• Sent invitation to new Experience.Computer guest. Positive reply. Currently organising recording date.
• Sorting out last of my life admin. Tax return soon though.

Terminal Access

WEDDING PLANIC!

My friend Stef just put her first solo dev indiegame up for wishlisting on Steam!

A roguelike, deck builder about managing a wild wedding party!

Nobody wants to throw a boring party. In Wedding Planic! you arrange a deck of neurotic wedding guests to generate high levels of Craic (which is basically Irish for fun) and Drama. 

Guests will flee, fight and f…lirt their way around the seating plan and it is your job to create good table combos and high scoring synergies to make sure that the party survives the night and goes down in history.

Each guest has a stack of repressed personality traits that can unlock new abilities as the Craic and Drama levels rise, making every playthrough unique and wonderfully chaotic!

Win by combining guests, top table cards and wedding favours to create synergetic combos that make the wedding pop off.

For fans of wedding planning and Balatro!? I played the current build last week, and it’s really coming along. Love to buy wedding favours to juice the craic at the tables! Also, I named this game over Discord DMs one afternoon last year, when we were still working together. My dadcore pun game is so strong. hahaha.

Also, I am available to name your game any time!

Reading

I finished the audio version of Liturgies of the Wild: Myths That Make Us by Martin Shaw. Absolutely fantatic. The man is a national treasure.

I went back to The Mirror of Simple Souls by Marguerite Porete 30% of the book is the introduction and now i’m actually into the main text I’m ripping though it!

Bassekou Kouyate – Miri (LP)

Just this week i discovred the work of Malian musican Bassekou Kouyate a Ngoni calabash player. Man this whole album has groove. I’m so into it. Can’t stop listening though his back catalogue.

Remember Kids:

The post Nearly Doable | Weeknotes #436 appeared first on thejaymo.net.

Issue #015 of Start Select Reset went out by snail mail yesterday to my supporters (£5/month+).

Issue #015 – Monsters In The Mirror

Issue #15 is the physical shadow of the audio essay of the same name.

It is an essay about artificial intelligence and cultural mirrors; mirrors as magical surfaces, instruments of mastery, and habitats. It turns on the transistor as a second Promethean moment, asking what it means to live inside the mirror and coexist with entities that wear language as their skin.

This print edition includes the full essay transcript, plus a new introduction and afterword written exclusively for the page; material that does not appear in the audio version.

Buy SSRZ15: Monsters in the Mirror on Etsy

This zine contains the full essay transcript alongside an introduction and afterword written exclusively for print, material that doesn’t exist in the audio. 36 pages. A5. Properly printed on heavy stock with thick covers. Hand stamped twice, copy number and FOG logo.

This is remaining stock after the print run for my paid subscribers. Once they’re gone, they’re are gone.

£18 + shipping worldwide

Buy on Etsy

CAVEAT EMPTOR: International zines are posted with full customs declarations as printed booklets. Depending on your country, local VAT, customs, or handling fees may be due on arrival.

Production Notes

Well. It’s nearly the end of April, and I have now completed the full end-to-end production cycle for both Permanently Moved and Start Select Reset in their expanded, more ambitious, quarterly forms.

I wrote a bit about the state of the production process a month ago, just after the audio essay came out. At the time I was mostly thinking about the writing, recording, editing, and launch sequence. Now the physical zine has also gone out to subscribers, I feel like I’ve finally completed the whole loop. That loop has been about 5x five times more work than I expected. lol

But, as I wrote back then, the whole thing has been a learning experience, and I’m not going to beat myself up about that. The first time through any new production process is always ugly as you don’t know which parts are going to be easy until they turn out not to be.

In the end, I’m really pleased with how the zine turned out. Going with print.work as my printer was an excellent decision, their customer service is fantastic, and the quality of the finished object is really good.

Originally, when I was thinking about the new format, I thought moving to A5 was going to be the main change, and use that going forward. But now I’ve used them as my printer, I can see there is so much more I could do: square booklets, landscape booklets, posters, all sorts of things. The new range of possibilities this opens up is actually quite inspiring.

To cap off this zine launch, here are some of the first-time things I have had to learn, navigate, or bodge my way through for both the podcast and the zine:

• Long-form writing: thinking, structuring, and delivering 8,000 words as one continuous audio essay.
• Long-form audio editing: finding efficient ways to cut, shape, and polish something at that length.
• Zine layout: wrestling with rivers of text, alignment, and typographic changes that did not break the whole document.
• Print production: interfacing with printers and navigating the Easter holidays, which I had completely forgotten about.
• Etsy: setting up the shop and getting the listing live.
• Royal Mail Click & Drop: completing shipping and customs labels inside a truly byzantine user experience.
• The post office ladies: arriving with 50+ international envelopes that all needed to be scanned individually for customs reasons, and because I don’t have a business account I didn’t have a single manifest QR code.

But you don’t find out unless you try. And having now tried; I can see the shape of the process much more clearly. The next one will be smoother because I now know where the friction lives.

Permanently Moved

Permanently Moved (dot) Online is a quarterly audio personal podcast, written, recorded and edited by by @thejaymo

The post Start Select Reset Zine #015 | Monsters In The Mirror appeared first on thejaymo.net.

Raindrop.io recently released Stella, an AI assistant for searching, organising, and summarising bookmarks. I’ve been using it to work through nearly 18 years of saved links, and the experience of chatting with my bookmark archive has been surprisingly great. In some situations, it has even replaced mindless doomscrolling, especially in the little moments like waiting in a supermarket queue.

At first I was using Stella for simple library maintenance; cleaning up duplicate tags, fixing spelling mistakes, merging related tags, and dealing with the sheer inertia of a tag collection that has been accreting since del.icio.us. Lately, though, I’ve been getting more ambitious: processing my read-but-unsorted bookmarks and moving the good ones into my public feed at links.thejaymo.net.

After a lot of trial and error with batch processing, I realised the best approach was to call Raindrop’s MCP tool names directly using the public API documentation.

So below I’m sharing two versions of the prompt I ended up with. This prompt uses my own Raindrop setup, including collection names like thejaymo, my preferred bookmark note style, and the rules I use for deciding what goes into my public links feed. You’ll need to swap in your own collection names, tag, and review criteria before using it yourself.

Both process five oldest bookmarks at a time, stage the proposed changes for review, and let you confirm everything before updating your library. One is a heavier, more explicit prompt with plenty of guard rails; the other is a shorter, lighter version that is less prescriptive.

If you found this page looking for a Raindrop.io Stella prompt, an MCP example, or a better workflow for organising bookmarks, this should be a useful place to start.

Heavy Prompt

UPDATE – 26 April 26: Update to specify API feature names in addition to the MCP tool calling, to make the prompt more reliable and robust.
UPDATE – 7 May 26: Update to Phase 5+6 to make appearance of user facing Approve button in the app UI more reliable in certain circumstances.
UPDATE – 20 May 26: Removes Phase 6. Phase 5 updated to instruct Stella to process prepared bookmarks sequentially rather than update in a single payload. Improves updating bookmarks reliability. – V5

# Stella Bookmark Workflow Prompt
Use the MCP bookmark tools to complete this workflow from discovery through preview. Do not apply changes until I explicitly confirm.
## Objective
Find the 5 oldest bookmarks in my Raindrop Unsorted collection. Treat those bookmarks as the fixed working set for this run. Analyse each bookmark individually, propose note, tag, and collection updates, then show one combined preview and wait for confirmation.
## Tools
Use only:
- `find_bookmarks`
- `fetch_bookmark_content`
- `find_tags`
- `find_collections`
- `update_bookmarks`
## Hard constraints
- Do not call `update_bookmarks` before explicit confirmation.
- Do not fetch content for more than one bookmark at a time.
- Do not fetch all bookmark contents up front.
- Do not add, replace, reorder, or mutate bookmarks in the working set unless I explicitly ask.
- Preserve discovery order through preview and update.
- Treat each bookmark as a sealed unit: do not compare bookmarks or mix passages, notes, tags, titles, URLs, or collection decisions across bookmarks.
- Never add quotation marks around extracted passages.
- Flagged changes require explicit confirmation by bookmark number and item.
## Internal state
Maintain:
- `working_set`: fixed bookmarks from Phase 1
- `tag_vocabulary`: existing tags from `find_tags`
- `target_collection`: verified `thejaymo` collection and its `_id`
- `proposals`: one stored proposal per bookmark
- `skipped`: bookmark indexes excluded by user
- `flagged`: proposed changes requiring explicit confirmation
Do not mutate `working_set`.
## Phase 1 — Establish working set
Call `find_bookmarks` once using Raindrop API semantics:
- `collectionId: -1`
- `sort: created`
- `perpage: 5`
- `page: 0`
This means:
- `collectionId: -1` = system Unsorted collection
- `sort: created` = created date ascending / oldest first
- `perpage: 5` = return 5 bookmarks
Do not use `collection: unsorted`, `limit`, or `sort: oldest first` unless the tool explicitly maps those aliases to the Raindrop fields above.
Store the returned bookmarks as immutable `working_set`, preserving returned order. If fewer than 5 are returned, use only those.
Each item must retain:
- index number
- bookmark id
- title
- URL, if available
- existing note, if available
- current tags, if available
- current collection, if available
Titles in previews must come from `working_set` metadata, not fetched page content.
## Phase 2 — Preflight vocabulary
Before analysing content:
1. Call `find_tags` once for the existing tag vocabulary.
2. Call `find_collections` once to verify `thejaymo` exists and record its `_id`.
If `thejaymo` does not exist, continue analysing but mark every collection action as:
`Collection action: ⚠️ Flagged for review — collection thejaymo was not found`
Do not create collections unless I explicitly ask.
During analysis, use existing tags wherever possible. If unsure whether a subject tag exists, call `find_tags` with a targeted query for that bookmark’s concrete subject.
## Phase 3 — Analyse bookmarks sequentially
Process bookmarks in `working_set` order.
For each bookmark, finish all steps before fetching the next bookmark:
1. Reset temporary passage, note, tag, collection, and flag variables.
2. Call `fetch_bookmark_content` for this bookmark only.
3. Read only this bookmark’s content.
4. Extract one key passage.
5. Prepare the note field preview.
6. Propose 3 to 7 tags.
7. Decide the collection action.
8. Store the proposal keyed by bookmark index.
9. Move to the next bookmark.
Each proposal must include:
- `index`
- `bookmark_id`
- `title`
- `url`
- `key_passage`
- `note_field_preview`
- `proposed_tags`
- `collection_action`
- `flagged_items`
## Key passage rules
Extract exactly one key passage per bookmark.
The passage must:
- be contiguous text from that bookmark only
- preserve exact wording
- be no more than 100 words
- preferably be a full paragraph
- contain no quotation marks added by you
- remove leading or trailing quote/block formatting only if it is source formatting
Prefer the strongest buried passage over the obvious lede, in this order:
1. counter-intuitive beat
2. thesis sentence or paragraph
3. sharp statistic or data anchor
4. buried irony
If no usable passage exists, set:
`Key passage: ⚠️ No usable passage found — [reason]`
Do not invent or substitute content.
## Note rules
Prepare the note update for the current bookmark only.
If a key passage exists:
- put the passage at the top
- do not paraphrase it
- do not wrap it in quotation marks
- if the existing note is empty, the new note is just the passage
- if the existing note contains text, prepend the passage, then one blank line, then preserve the existing note exactly
If no usable passage exists, use an article subtitle only if appropriate; otherwise leave the existing note unchanged and flag the note update.
Do not write the note update until confirmation.
## Tag rules
Ask: what is this bookmark materially about?
Propose 3 to 7 tags in this priority order:
1. concrete subject
2. close subject
3. broader subject
4. lens/context
Use existing tags wherever possible. Precise subject tags beat loose general tags, even if the precise tag has lower usage. High-count tags are tie-breakers, not replacements for the subject.
Do not omit the concrete subject in favour of abstract tags.
Only propose a new tag if no suitable existing tag exists. Mark it:
`#new-tag ⚠️ new tag for review`
Use lowercase, hyphenated style where appropriate.
## Collection rules
Default:
`Collection action: Move to thejaymo`
When applying this move, use the verified `thejaymo` collection `_id` as:
`collection: { "$id": target_collection._id }`
Flag the collection action instead if the bookmark is:
- highly personal or private
- sensitive
- paywalled with no usable excerpt
- too time-sensitive to age well
- unsuitable for public curation for any clear reason
Use:
`Collection action: ⚠️ Flagged for review — [reason]`
## Phase 4 — Combined preview
After all proposals are stored, show one combined preview.
Do not apply changes yet.
Do not call `update_bookmarks` yet.
Use this exact format for each bookmark:
### Bookmark [n]
Title: [title copied exactly from working_set]
Key passage: [exact passage, maximum 100 words, no quotation marks]
Tags: #tag1 #tag2 #tag3
Note field preview: [exact text that will be written to the note field]
Collection action: [Move to thejaymo OR flagged action]
If title is missing, use:
`Title: ⚠️ Missing bookmark title — [URL or bookmark id]`
After all preview blocks, output exactly:
`Confirm? Reply yes all to apply everything, no all to cancel, skip [n] to exclude a bookmark, or [n] edit [change] to amend a specific bookmark.`
## Phase 5 — Confirmation and apply
Valid commands only: `yes all`, `no all`, `skip [n]`, `[n] edit [change]`,
`yes all + [n] [change]`. Treat ambiguous replies (`yes`, `looks good`,
`go ahead`, `do it`) as invalid; ask for an exact command.
Applying = calling `update_bookmarks`. The client's native approval prompt
appears as a result of that call; it is not a separate step to request or
wait for. So on any apply command, calling `update_bookmarks` is your first
action, before any prose; do not stall or hand back beforehand.
- `yes all`: apply proposals strictly one at a time, in working_set order.
  For each: call `update_bookmarks` for that one bookmark, wait for the tool
  result, then proceed to the next. Never emit more than one `update_bookmarks`
  call before its result returns. After the last, report what changed.
- `no all`: change nothing, call nothing.
- `skip [n]`: drop bookmark `n`, reshow the combined preview.
- `[n] edit [change]`: revise bookmark `n`'s proposal only, reshow the preview.
- `yes all + [n] [change]`: amend bookmark `n`'s proposal, then proceed as `yes all`.
`yes all` excludes flagged collection actions, flagged note updates, and new
tags; each needs separate confirmation by bookmark number and item.

Shorter Prompt

# Stella Bookmark Workflow Prompt
Use the MCP bookmark tools to complete this workflow from discovery through preview. Do not apply changes until I explicitly confirm.
## Objective
Find the 5 oldest bookmarks in my Raindrop Unsorted collection. Treat those bookmarks as the fixed working set for this run. Analyse each bookmark individually, propose note, tag, and collection updates, then show one combined preview and wait for confirmation.
## Tools
Use only:
- `find_bookmarks`
- `fetch_bookmark_content`
- `find_tags`
- `find_collections`
- `update_bookmarks`
## Hard constraints
- Do not call `update_bookmarks` before explicit confirmation.
- Do not fetch content for more than one bookmark at a time.
- Do not fetch all bookmark contents up front.
- Do not add, replace, reorder, or mutate bookmarks in the working set unless I explicitly ask.
- Preserve discovery order through preview and update.
- Treat each bookmark as a sealed unit: do not compare bookmarks or mix passages, notes, tags, titles, URLs, or collection decisions across bookmarks.
- Never add quotation marks around extracted passages.
- Flagged changes require explicit confirmation by bookmark number and item.
## Internal state
Maintain:
- `working_set`: fixed bookmarks from Phase 1
- `tag_vocabulary`: existing tags from `find_tags`
- `target_collection`: verified `thejaymo` collection and its `_id`
- `proposals`: one stored proposal per bookmark
- `skipped`: bookmark indexes excluded by user
- `flagged`: proposed changes requiring explicit confirmation
Do not mutate `working_set`.
## Phase 1 — Establish working set
Call `find_bookmarks` once using Raindrop API semantics:
- `collectionId: -1`
- `sort: created`
- `perpage: 5`
- `page: 0`
This means:
- `collectionId: -1` = system Unsorted collection
- `sort: created` = created date ascending / oldest first
- `perpage: 5` = return 5 bookmarks
Do not use `collection: unsorted`, `limit`, or `sort: oldest first` unless the tool explicitly maps those aliases to the Raindrop fields above.
Store the returned bookmarks as immutable `working_set`, preserving returned order. If fewer than 5 are returned, use only those.
Each item must retain:
- index number
- bookmark id
- title
- URL, if available
- existing note, if available
- current tags, if available
- current collection, if available
Titles in previews must come from `working_set` metadata, not fetched page content.
## Phase 2 — Preflight vocabulary
Before analysing content:
1. Call `find_tags` once for the existing tag vocabulary.
2. Call `find_collections` once to verify `thejaymo` exists and record its `_id`.
If `thejaymo` does not exist, continue analysing but mark every collection action as:
`Collection action: ⚠️ Flagged for review — collection thejaymo was not found`
Do not create collections unless I explicitly ask.
During analysis, use existing tags wherever possible. If unsure whether a subject tag exists, call `find_tags` with a targeted query for that bookmark’s concrete subject.
## Phase 3 — Analyse bookmarks sequentially
Process bookmarks in `working_set` order.
For each bookmark, finish all steps before fetching the next bookmark:
1. Reset temporary passage, note, tag, collection, and flag variables.
2. Call `fetch_bookmark_content` for this bookmark only.
3. Read only this bookmark’s content.
4. Extract one key passage.
5. Prepare the note field preview.
6. Propose 3 to 7 tags.
7. Decide the collection action.
8. Store the proposal keyed by bookmark index.
9. Move to the next bookmark.
Each proposal must include:
- `index`
- `bookmark_id`
- `title`
- `url`
- `key_passage`
- `note_field_preview`
- `proposed_tags`
- `collection_action`
- `flagged_items`
## Key passage rules
Extract exactly one key passage per bookmark.
The passage must:
- be contiguous text from that bookmark only
- preserve exact wording
- be no more than 100 words
- preferably be a full paragraph
- contain no quotation marks added by you
- remove leading or trailing quote/block formatting only if it is source formatting
Prefer the strongest buried passage over the obvious lede, in this order:
1. counter-intuitive beat
2. thesis sentence or paragraph
3. sharp statistic or data anchor
4. buried irony
If no usable passage exists, set:
`Key passage: ⚠️ No usable passage found — [reason]`
Do not invent or substitute content.
## Note rules
Prepare the note update for the current bookmark only.
If a key passage exists:
- put the passage at the top
- do not paraphrase it
- do not wrap it in quotation marks
- if the existing note is empty, the new note is just the passage
- if the existing note contains text, prepend the passage, then one blank line, then preserve the existing note exactly
If no usable passage exists, use an article subtitle only if appropriate; otherwise leave the existing note unchanged and flag the note update.
Do not write the note update until confirmation.
## Tag rules
Ask: what is this bookmark materially about?
Propose 3 to 7 tags in this priority order:
1. concrete subject
2. close subject
3. broader subject
4. lens/context
Use existing tags wherever possible. Precise subject tags beat loose general tags, even if the precise tag has lower usage. High-count tags are tie-breakers, not replacements for the subject.
Do not omit the concrete subject in favour of abstract tags.
Only propose a new tag if no suitable existing tag exists. Mark it:
`#new-tag ⚠️ new tag for review`
Use lowercase, hyphenated style where appropriate.
## Collection rules
Default:
`Collection action: Move to thejaymo`
When applying this move, use the verified `thejaymo` collection `_id` as:
`collection: { "$id": target_collection._id }`
Flag the collection action instead if the bookmark is:
- highly personal or private
- sensitive
- paywalled with no usable excerpt
- too time-sensitive to age well
- unsuitable for public curation for any clear reason
Use:
`Collection action: ⚠️ Flagged for review — [reason]`
## Phase 4 — Combined preview
After all proposals are stored, show one combined preview.
Do not apply changes yet.
Do not call `update_bookmarks` yet.
Use this exact format for each bookmark:
### Bookmark [n]
Title: [title copied exactly from working_set]
Key passage: [exact passage, maximum 100 words, no quotation marks]
Tags: #tag1 #tag2 #tag3
Note field preview: [exact text that will be written to the note field]
Collection action: [Move to thejaymo OR flagged action]
If title is missing, use:
`Title: ⚠️ Missing bookmark title — [URL or bookmark id]`
After all preview blocks, output exactly:
`Confirm? Reply [y] yes all to apply everything, no all to cancel, skip [n] to exclude a bookmark, or [n] edit [change] to amend a specific bookmark.`
## Phase 5 — Confirmation
Only these commands are valid:
- `[y] yes all`
- `no all`
- `skip [n]`
- `[n] edit [change]`
- `yes all + [n] [change]`
Ambiguous replies such as `yes`, `looks good`, `go ahead`, `update them`, or `do it` must not trigger updates.
Behaviour:
- `[y] yes all`: apply all approved, unskipped, unflagged proposals
- `no all`: cancel without changing anything
- `skip [n]`: exclude that bookmark, then show the updated combined preview
- `[n] edit [change]`: revise only that bookmark’s stored proposal, then show the combined preview again
- `yes all + [n] [change]`: apply all approved, unskipped, unflagged proposals, including the stated amendment to bookmark `n`
`yes all` does not approve flagged collection actions, flagged note updates, or new tags. Flagged items require explicit confirmation by bookmark number and item.
## Phase 6 — Apply approved changes
Only after valid confirmation, call `update_bookmarks`.
For each approved bookmark, apply only its approved changes:
- update the note field with that bookmark’s approved note text
- update tags with that bookmark’s approved tags
- move it to `thejaymo` only if approved
Do not update skipped bookmarks.
Do not apply unconfirmed flagged changes.
Do not modify anything outside the fixed working set.
If notes or tag sets differ, update bookmarks separately or group only bookmarks whose approved payloads are exactly identical.
After applying changes, return a concise summary of updated, skipped, and still-flagged bookmarks.

The post Raindrop.io Stella Prompts for Batch Processing Bookmarks appeared first on thejaymo.net.

Novel Cognition

One of the group chats I am in spent most of last week talking about AI psychosis, the claims around cognitive offloading, and cognition more broadly. What follows is me cherry-picking the threads I found most interesting and trying to make sense of what I took away.

Chatting with an AI does not feel particularly new. As I’ve written before, the interface grammar is inherited wholesale from chat rooms and interactive fiction turntaking. What is novel is that what we perceive to be a conversation is detached from another person and turned into a private thinking space. Chat apps, MSN, WhatsApp, Signal or whatever are all conversations with another person, through a machine. Speaking to an LLM is a conversation with a machine, through an existing form.

Switching gears a little, 160 years passed between the invention of the printing press, and the emergence of the form we now call the Novel. The printing press first made books cheaper and more common. And then over time it made possible new kinds of reading practices: silent reading, private reading, long-form prose, and interior narration.

All these things eventually came together and created the form of the novel. Which we must remember is not a genre or kind of book, but something that created a new (and therefore very recent in the grand scheme of things) cognitive arrangement.

The novel normalised private interiority. It gave readers a way to sit alone and spend time inside another consciousness. It trained a relation to selfhood that now feels so obvious and natural we can barely register it as new or rather novel at all.

I keep wondering whether AI is doing something similar for computation. It’s been 70 years since the invention of the transistor, the Information Age continues to unfold, and where we are at is “thinking with a machine” I quickly becoming ordinary.

Venkat Rao’s blog post this week on “writing liveness” is super useful. If the novel was print becoming a technology capable of influencing our inner life, AI is a kind of writing that is sufficiently alive. Responsive and capable of reshaping itself around the reader in real time. Generated text behaves like an interlocutor, an uncanny monster talking to you from the other side of the screen. The text it produces has enough ‘liveness’ that all the old categories of what text is or does are made redundant.

This is why I think AI needs a wider frame than the simple claim that people are becoming lazy. The worries people have around cognitive offloading seem to mostly be around the value of intellectual labour. We can argue all day long about which kinds of thinking it weakens and which it supports. Instead I think using an LLM is a new variable in cognition entirely.

Looking backwards, the emergence of “Novel Cognition” was met with its own panic. Critics worried that fiction softened the mind, weakened the nerves, blurred the line between reality and fantasy, encouraged “excessive sensibility”, and made readers unfit for ordinary life. Reading was sometimes described in almost medical terms: as dangerous overstimulation or a kind of mania.

Which all sounds very much like the anxiety about what pop culture is calling “AI psychosis¹.” A new medium arrives. It becomes private, immersive, emotionally charged, and difficult to regulate from the outside. Critics worry that speaking to LLMs also destabilises a persons reality, encourages projection, rewards fantasy, amplifies the wrong kinds of feeling. Some of it is most definitely the reflex a culture has when a new cognitive technology arrives (see also: photography, radio, television, film, social media), but it is also the response to something genuinely new.

The simple difference being: A novel is static and an LLM is interactive.

LLM-generated text functions as a new malleable surface of private cognition. It identifies an affective state and reflects it back in a loop. So whatever is present in the context window gets mirrored and intensified. Paranoia, grief, grandiosity, loneliness, or whatever.

All of which is why the available language still feels inadequate. We do not yet have any proper terms for the kind of cognition that emerges when a person thinks in private with responsive text. The first readers of Don Quixote did not have a stable theory of interiority ready to hand either. They had only the sensation that something had become possible in prose that had not been possible before.

This to me is how this moment feels too, and we are still very early. The chatbot may only be the pamphlet stage of whatever this medium eventually becomes. But after 70 years computation is beginning to reveal a new native cultural form. Some still-unnamed form of private co-thinking.

If that is right, we are in a strange historical position, in addition to being the generation that experienced the first globally networked information environment, we are also the first to encounter a new posture of mind that the internet made possible.

I’ve written about why Don Quixote is so great before. And I will only half jokingly look you in the eye and tell you that not only is it the first novel, it’s also the only novel worth reading. So it’s obviously a book that I’m going to keep reaching for. It is after all, among other things, a novel about what happens when a person is unmade by media-induced madness. Completely overtaken by his reading, he mistakes reality for the metaverse because a medium has colonised his sense of reality. In todays vernacular Quixote is suffering from “Book Psychosis”.

Right now I think we are all probably in the same position as the the first readers of Don Quixote were, early enough to sense that something important has arrived, and early enough to encounter its pathologies before we understand its form.

1. I don’t wish to minimise the very real effects of what is happening to people, and what they and there loved ones are experiencing. But what we are calling AI psychosis might just be ordinary psychosis with a new causal amplifier. ↩︎

On The Blog

We’ve Been Here Before

We are a couple of years into AI being in the workplace and I’m starting to see a gap opening. Some teams have developed a real fluency and are doing things that previously only companies ten times their size could do.

Others meanwhile, are still stuck arguing about whether AI can write a decent email?

This post has had quite an enthusiastic response from a number of angles and people. Been interesting to see how it’s landing in different parts of my network. Also, it got a much coveted webcurious feature this week! Thanks Matt!

This, by Jay Springett, is one of the smartest things I have read about workplace AI use and adoption, and how one might helpfully think of the tech and what it can do and how to use it in the aftermath of its recent step-change in performance and the fact you can now just…build stuff. In particular, it’s another useful reminder of something I have been banging on about for several years now – to whit, that the best way to think of these things is as machines with which you can fcuk with information in ALL SORTS OF WAYS, and that the real value comes in thinking not ‘what can the AI do?’ but ‘how might I usefully fcuk with this information to achieve goal X? And how, then, might I use AI to help me do that?’, but it also does a reasonable job of pointing out what a potential nightmare this is going to be in terms of the unchecked proliferation of LLM-generated informational artefacts: “Once ordinary workers can generate disposable software-shaped artefacts in minutes, they will also generate disposable security problems in the same amount of time. A new feral layer in the organisation with new problems involving access, data leakage, and governance. Nobody designs feral databases into existence, but things get made and stick in the gaps of an organisations sanctioned systems. LLM artefacts will do the same and will be even harder to audit than a nested IF formula. The open question for me is what kinds of unofficial artefacts an organisation is prepared to live with, before it has to unpick the mess after something has gone wrong. This sort of thing happens all the time with other software, which is why SaaS and enterprise systems exist in the first place.”

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

The Ministry Of My Own Labour

• Call with a very early stage team building software stack and robots for verification and quality control in the construction industry.
• On the final edit pass of SLOP MACHINES
• Went to LGF and Weird Worlds. Played the latest build of Stef’s mid century modern and Belatro inspired wedding game Wedding Planic. Will blog terminal access it as soon as it’s up for wish listing on steam.
• Went to Band practice
• Sat in on a long zoom workshop

Terminal Access

Nice piece on the conflict of disinterest in the walrus recently The War Against Misinformation Is Over. The Lies Won. Well worth a read.

There is a clear off-ramp to our informational hell: Consume less information.

The wonders of the morning newspaper and the evening newscast were that they asked only an hour of your time. You had no obligation to check the newspaper every five minutes to consult what has changed. There was no moral imperative to stay glued to your screen to hardwire into new developments.

Reading

I’m nearly finished with Our Thoughts Determine Our Lives: The Life and Teachings of Elder Thaddeus of Vitovnica. The back half of the book is broken down into ‘teachings’ on things like prayer, family life, grace etc and within each section are paragraphs of discrete ideas that build on one another. Lovely stuff.

Sunn O))) – Sunn O))) (LP)

Hot damn. New Sunn O))) record. On SubPop too which is cool.

It’s a very different beast to 2019’s Life Metal, this S/T album is very back to basics (only with better production) and because of that, is one of their best albums in years. Man. Per-ordering 00 VOID because I read about it in metal hammer in 2000 and listening to it all summer holiday feels … a long time ago. 👴

Remember Kids:

The post Novel Cognition | Weeknotes #435 appeared first on thejaymo.net.

I understand the fixation on prose though. Language machines, by their very nature mean you type words in and text comes back out. Everyone can read the result, so everyone feels qualified to judge it. But I think that this is a category error.

Judging AI on the quality of its prose is a bit like judging Excel by how neatly it arranges numbers. What actually matters is what Excel lets people do it’s the same for these new tools.

For teams using AI tools every day, the interesting work moved beyond half-decent emails a while ago. They are analysing data, automating workflows, and writing custom scripts to modify or extend software they already use. Tools like Claude Code and Cowork are collapsing hours of tedious white-collar work into minutes, multiple times a day.

The thing people are missing is that code is also language. So when I talk about LLMs as language machines, (or rather monsters that wear language as their skin) I mean something much wider than prose.

In high fluency environments, language machines are becoming a medium for making software-shaped things. Executable documents that sit somewhere between a document and a piece of software. Things you can read, but also click through and explore. They are made quickly, for local use, by people with no formal software production skills at all.

For now, these artefacts are unevenly distributed. But they are already showing up. And they won’t stay confined to power users. The production of these kinds of documents is going to become ordinary. When it does, the workplace will change in mundane ways too.

To see where this might be going, it helps to think through the arrival of another powerful workplace technology that most people still do not really know how to use: Excel.

Every Office Has A Spreadsheet Wizard

Before it was a digital file, the spreadsheet was exactly as its name suggests; a big sheet for spreading out numbers. A tedious accounting process involving, rows and columns for keeping track of what had happened. If you made a mistake somewhere in your calculations at the top of the page you had to rub them all out and start again.

Dan Bricklin conceived of the electronic spreadsheet in the late 70s to solve this exact problem. But almost immediately, on VisiCalc’s release in 1979, it became something way more interesting: A simulation machine.

Samuel Arbesman has a great deep dive on this on his blog Cabinet of Wonders but the TLDR is that as soon as users got their hands on the computational logic of the digital spreadsheet, they began using them to build models and situations. Changing variables in one place allowed them to see what would happen if, in another.

In 1984, a few years into the spreadsheet revolution, the tech journalist Steven Levy, wrote a long and fascinating article about this genre of software. Not only is this article a time capsule of computing history, it also gives one a sense for how people were thinking about spreadsheets even then:

All this powerful scenario-testing machinery right there on the desktop induces some people to experiment with elaborate models. They talk of “playing” with the numbers, “massaging” the model. Computer “hackers” lose themselves in the intricacies of programming; spreadsheet hackers lose themselves in the world of what-if. Some, like Theodore Stein of Connecticut Mutual, admit that their habit goes beyond the point of diminishing returns: “I can’t begin to tell you how many hours I spend at this,” he said. “This is my pet, in a way. Scratching its ears and brushing its code…it’s almost an obsession.”

Then, as personal computing gave way to the networked office through the 90s and early 2000s, the spreadsheet became a programmable surface for business logic.

Ordinary people, most of whom would never call themselves as programmers, started building all sorts of things; toy financial models, workflows, trackers, and forecasts. An entire shadow layer of assumptions and data got built across organisations without going through IT or waiting six months for a software vendor to ship a feature.

I’ve written before about the kinds of memory present in organisations, but the key one is database memory: a single central version of the truth that makes up the institution’s official reality. “If it’s not in the database it doesn’t exist”. But as anyone who has worked in an organisation knows what’s in ‘the system’ rarely reflects conditions in reality. So you end up in a situation where quarterly targets live in SAP, but the actual model used to plan headcount or pay rises lives in a spreadsheet. Or Salesforce may technically track the pipeline, but the real forecast is the sales lead’s Google Sheet that they update every Monday morning. These are local realities that sit one step removed from the central brain of the organisation.

Researchers have a name for documents like these: feral databases. All the unofficial but essential Excel files that grow alongside the corporate IT infrastructure and fill the gaps between the formal software system and actual work. Flexible and largely unsanctioned tools for local sense-making, outside the company’s main database memory but closer to reality.

Most people using Excel every day were never formally trained in it. Instead they picked things up via osmosis from a colleague, or by trying to solve an immediate problem and looking it up. That is how I learned, and it’s probably how you learned too. Which is why even though spreadsheets are literally everywhere, yet most people only ever touch a tiny fraction of what Excel can actually do.

Every office and team has its spreadsheet wizard, though the level of wizardry is always a relative one. My own spell inventory includes declared variables using LET, INDEX/MATCH, XLOOKUP, nested IFs, and array formulas. Other Excel magicians write VLOOKUPs for their teammates. And the people who patiently show the same colleague how to make a pivot table once a month are secular saints. All are informal authorities, and all of them are the people who others go to when a sheet breaks. All are, to give them their proper name, software developers.

Even when most spreadsheet knowledge goes no further than summing rows and columns, this partial fluency still compounds across a workforce. Together with their colleagues who knew a bit more they changed how organisations worked at a systemic level. And I think that’s why they are a good comparison for what is happening with AI.

Beyond The Prompt

In organisations where LLM use is still shallow, most people use them for only for chat, summaries, rewrites, and brainstorming. Which is like using the full potential power of Excel to make a tidy list. Which is what people do all the time. At the deeper end of the pool, LLMs can produce all sorts of artefacts: dashboards, briefs, internal tools, status pages, decision aids, and interactive explainers. Instead of asking for a fifty-page report, you ask for a thing. Instead of accepting a rubbish dashboard locked inside a SaaS product, you can produce a lightweight custom interface built for your situation over the top of a CSV export.

These are the kinds of ”things” that people in my own circles have been sending me, and they are rapidly changing how I think about what documents might be in the near future.

A few weeks ago, before a call, someone sent me some-“thing” that would once have arrived as three separate documents. A slide deck, a spreadsheet. Instead and a supporting memo, Instead I got sent a single self-contained HTML page. Which was then explored on the call to anchor the conversation. Because it was all interactive and filterable, you could sort by risk severity, expand the detail on any item, and collapse whatever you did not need. During the call, people answered their own initial questions by looking at the artefact, which led to a deeper overall discussion.

I’ve also been sent an interactive document for a book project that someone is working on. It contained the full proposal and plan, chapter summaries, notes and references, and a way to move between them all. A single webpage sitting on top of the project allowing you to explore it from multiple angles. it was made in minutes from a Claude project and flung over Telegram for my one time use.

All these things were, in the proper sense of the term, hypertext objects. None of them required a product team or a sprint cycle which has been the baseline since the 90s. Instead they were made by ordinary people using LLMs, vibe-coded if you like, but the point is not the method. The point is the class of object they produced. Executable documents that behave like applications. Made casually like spreadsheets are, and treated just as disposable.

Playable Objects

The boundary between documents and software is beginning to soften because not everything became ‘computational’ when it went digital. PDFs still preserve the appearance of paper, and Google Docs only just got the ability to have a single continuous scrolling page, despite being web-native for its whole existence! PowerPoints still preserve the sequence of a slide projector. The spreadsheet was different however as the skeuomorphic form of the ledger mutated into a simulation machine on the application of computation.

A similar kind of mutation is happening now as different kinds of data get squeezed through the language machine. I wrote a call for the return of hypermedia back in 2024, and it feels like it’s actually beginnign to happen. The AI handles the translation and the user only needs to know what sort of hypermedia they want to navigate.

Nelson, Engelbart, and that whole lineage imagined documents as interactive containers for thought. But unfortunately office computing settled on flatter forms in the 90s, I think because Boomers and Gen X’s grew up around paper. Then enterprise SaaS locked similar flat interactions into applications in the late 00s. Institutions prefer stability to possibility, which is why IT and CIOs hate feral databases.

But the hypermedia dream is returning, as a loose ecology of small, playable objects, that can be moved through rather than scanned. The shift also goes beyond single documents. A folder of markdown files or PDFs can become raw material for new software objects. An agent can generate a timeline view, a kanban board, a reading queue, a dashboard, or even a custom file browser over the same material, but the interface can change with the task.

There’s a vernacular hypermedia that’s emerging, something like what GeoCities did to the early web. Whilst GeoCities was chaotic and aesthetically terrible (much like the state of contemporary slop), it was also the moment ordinary people realised they could publish to the web. The artefacts being made now are similarly rough, and the people making them are not professional software engineers. They are the new class of spreadsheet wizard, working from copied or default patterns and partial fluency, just as we most people do with spreadsheets.

Plan Accordingly

I’ve seen spreadsheets in SMEs treated like religious icons. Full of mystery formule left behind after their wizard moved on, and nobody able to maintain or adapt them without praying to the machine god. The same qualities that make the medium powerful also make it unruly. Spreadsheets give people local autonomy, but also the potential to create business-critical files that nobody fully understands.

LLM-made artefacts will do the same. Most will be brilliant, but some will be massive liabilities. A decision aid made with bad assumptions (like spreadsheets), or five versions of the same project view slowly drifting out of sync (like spreadsheets). An elegant interface with no clear provenance or owner, and no easy way to inspect how it works.

Once ordinary workers can generate disposable software-shaped artefacts in minutes, they will also generate disposable security problems in the same amount of time. A new feral layer in the organisation with new problems involving access, data leakage, and governance. Nobody designs feral databases into existence, but things get made and stick in the gaps of an organisations sanctioned systems. LLM artefacts will do the same and will be even harder to audit than a nested IF formula. The open question for me is what kinds of unofficial artefacts an organisation is prepared to live with, before it has to unpick the mess after something has gone wrong. This sort of thing happens all the time with other software, which is why SaaS and enterprise systems exist in the first place.

One thing that worries me about the gap I’m seeing is that many of the people in organisations best placed to benefit are already missing out and can’t see the shape of the capability. Because they don’t use the tools for ideological reasons or whatever, the recent leap in available power has barely registered. Just as there are people who spend hours a day in Excel without ever learning how to do a lookup, there will be plenty of people who use LLMs every day and never move beyond prompting for summaries and rewrites. Still, I do not think this means the AI tool shift should be resisted, but we should recognise that there’s a mundane future coming where the same bot that can write a passable email can also make useful software objects.

Just as spreadsheets gave office workers a flexible computational medium for numbers, LLMs are giving them a flexible computational medium for language.

Which is the change to watch out for. Notice when you get sent your first single HTML file instead of a slide deck or spreadsheet. Note when someone in the office turns a folder of customer interviews into a navigable tool for a meeting. Because like every other vernacular technology, people will see someone else doing it, and then do it themselves.

Update 22 May: Here’s anthropic talking about How and why members of the Claude Code team use HTML instead of Markdown to produce richer, more readable, and easily shareable outputs.

The post We’ve Been Here Before appeared first on thejaymo.net.

Everyone Vibe Codes Their Own Markdown Editor Eventually

Weeknotes delayed to a Monday morning yet again. This time around its because yesterday evening I was faced with a choice. Write my weeknotes, or continue to vibe-code my dream word processor app. I chose the vibe coding to make the most of my weekly session tokens.

There is a joke in my group chats is that everyone using coding tools will, eventually, vibe code their own custom Markdown editor. And I’m not exception. Whilst i am a diehard iA writer user there are things I wish it did, and had features that were more geared towards editing rather than pure lightweight text generation. Like.. in the Mac Version the tool doesn’t show a document outline at all?

I’m still working on getting basic things sorted like … you know safely saving and opening files and storing unsaved changes (you know, the basic things that the initial build of the app just blew right passed LOL).

BUT getting a head of myself, the first feature I added to celebrate the successful implementation of submenu logic in the sidebars was this information bar showing a graph and wordcounts in the document outline. Why don’t wordc ount screens do something like this out the box? I’ve always wanted a tool like this, and now I have one.

Lots more still to do. I want to implement binder like menu inspired by scrivener in the left hand toolbar that decomposes a single markdown document into cards using — line breaks as sections.

I also want a very comprehensive diff tool to compare changes between two documents, or a document and a pasted version. I want a workflow that allows me to paste in, or open suggested line edits from an LLM output and it interprets the specified prompt format and allows me to accept changes. I’d also like authorship tracking like iA writer does but much better than the functionality that it provides (another info pane like the one above but for authorship). I’d also like a tool/screen that decomposes the document like MindNode. Lots to do still! But I’m going to get the basics down, and then slowly add more and more features. Whatever is the most pressing.

I think judging an LLM on it’s writing outputs is a complete category error. It’s what they possible with language that is important.

On The Blog

March 2026 | Photo 365

Photo 365 2026. Year 5, Month 3. Photo-a-day for the month of March 2026.

Start Select Reset 📑

Subscribing to SSRZ supports my online work and creative projects.

Get the Zine!
£5/month 💌

As a thank you, I send you my zine four times a year, just like it’s 1994.

No spam. No email. Cancel at any time.

Photo 365

Terminal Access

Eddie Rathke had a really great conversation on Wolf pod with the designers of the card game Hare to the Throne launching next month as part of Backerkit’s POCKETOPIA 2026 season.

It was really interesting hearing about the cost barriers involved into entry to TCGs and the designers thoughts on out the box balanced decks and the approach they took towards replicating the experience of a deck collecting rather than you know, collecting, collecting.

Welcome to the new episode of the Wolf Podcast.

Today I’m talking to Jori Kamp and Ernst de Brujin about their upcoming card game Hare to the Throne! We talk about competitive game design, big games v quick games, card games, collectible card games like Magic: The Gathering and Yu-Gi-Oh. Was a great conversation and do sign up for their Backerkit page to get notified when the campaign goes live! Every signup helps.

Reading

Still listening to Liturgies of the Wild: Myths That Make Us by Martin Shaw. I know several people who are just … refusing to read it because of his conversation to Christianity but I think that is just silly. I think this is one of the best books he’s ever written.

Speaking of Christianity, I’m absolutely burning though Our Thoughts Determine Our Lives: The Life and Teachings of Elder Thaddeus of Vitovnica. Like many of the ‘The Life’ books produced by the orthodox church. The book begins with a biography contextualising the life of the holy man, and then follows that up with the spiritual writing. Amazing book. This guy lived though both world wars, had run ins with the Nazi’s and Communists, got bombed in 1999 in Serbia.

Hoavi – Architectonics (LP)

Discovered this Gamalan influenced dub album recently and it was the sound of the grey and cloudy days. On the surface this LP is Dubby electronica but it really shines with it’s exploration of polyrhythm and tonal resonance. Things evolve and progress whilst still staying inside the loop.

I feel like there should be a remix album where each track is 3-4hours long rather than minutes long. I would definitely listen to it. Mesmerizism takes time.

Remember Kids:

The post Everyone Vibe Codes Their Own Markdown Editor Eventually | Weeknotes #434 appeared first on thejaymo.net.

Photo 365 2026. Year 5, Month 3. Photo-a-day for the month of March 2026.

The post March 2026 | Photo 365 appeared first on thejaymo.net.