Voltropy (@Voltropy) / X

Voltropy

45 posts

Voltropy

@Voltropy

AI from first principles.

Joined July 2025

Pinned
Voltropy
@Voltropy
Feb 16
ANNOUNCEMENT: We've built a coding agent that beats Claude Code on long tasks. Today we're releasing it for free. Meet Volt: The coding agent who never forgets. → Dominates Claude Code on the OOLONG long-context benchmark, including at every length from 32K to 1M tokens.
27K
Voltropy reposted
Dave Font
@davefontenot
May 22
Some founders are fighting for b2b saas. And others are fighting to win it all. This conversation is the moment I knew Ted and @ClintEhrlich were taking on Dario.
00:00
04:42
HFØ
@hf0
May 22
5 of 10 teams at demo day broke $10M annualized HF0 is not just for early stage companies Interviews started yesterday.
8.6K
Voltropy reposted
HFØ
@hf0
May 22
5 of 10 teams at demo day broke $10M annualized HF0 is not just for early stage companies Interviews started yesterday.
00:00
237K
Voltropy reposted
Josh Lehman
@jlehman_
May 18
lossless-claw 0.11.1 — the focus mode release 🎯 /lossless focus curates your context ↩️ /lossless unfocus brings the normal context view back 🖼️ image externalization now works across roles 📦 installs stop pulling a second OpenClaw
31K
Voltropy
@Voltropy
May 7
"LCM: Lossless Context Management" (Ehrlich and Blackman, 2026) is now available on arXiv. This is the paper that caused @openclaw to modify its architecture to support context management. It's a must-read for anyone interested in RLMs vs LCM.
arxiv.org
LCM: Lossless Context Management
We introduce Lossless Context Management (LCM), a deterministic architecture for LLM memory that outperforms Claude Code on long-context tasks. When benchmarked using Opus 4.6, our LCM-augmented...
1.4K
Voltropy reposted
Josh Lehman
@jlehman_
May 3
lossless-claw 0.9.3 — the "please just keep working" release 🧠 cache-aware compaction fires before overflow 🔁 fewer repeated old instructions 🧰 lcm tools load on OpenClaw 2026.5.2+ 🔌 Codex, DeepSeek, Bedrock fixes 🛡️ safer migrations, payloads, and replay
36K
Voltropy reposted
Stephen Schoettler
@SteveSchoettler
Apr 28
🚀 hermes-lcm v0.7.1 is live! 🧠 Compression rollover continuity 🔌 Provider-prefixed model routing 🧼 Thinking-tag cleanup Update: git -C ~/.hermes/plugins/hermes-lcm pull --ff-only Bounded context, unbounded memory. Nothing is ever lost. @Voscko @Teknium @NousResearch
Release v0.7.1 · stephenschoettler/hermes-lcm
From github.com
11K
Voltropy reposted
Dave Font
@davefontenot
Mar 26
Recursive self-improving AI is here. I had heard people talking about self-improving AIs at some of the frontier labs but wasn't sure how real it was. One of the neo labs in the current @hf0 batch had a breakthrough and now it’s running in our basement. It’s real.
25K
Voltropy
@Voltropy
Mar 26
The following is a statement meant for public consumption regarding the progress of Artificial Intelligence breakthroughs in Silicon Valley: Recursively self-improving AI is here.
HFØ
@hf0
Mar 26
Public Service Announcement:
535
Voltropy reposted
Martian Engineering
@MartianEng
Mar 18
Lossless Context in OpenClaw feat. Josh Lehman x.com/i/broadcasts/1…
605
Voltropy reposted
Josh Lehman
@jlehman_
Mar 16
Fun fact about lossless-claw: in addition to solving agent amnesia and enabling infinite-length sessions, it's also very token efficient. Lossless summaries are great for prompt caching. I at about a 90-94% cache hit rate. Thanks to incremental compaction, your context rarely
11K
Voltropy reposted
Clint Ehrlich
@ClintEhrlich
Mar 16
Why doesn't Anthropic just solve compaction by adding LCM to Claude? @Voltropy open-sourced LCM. It's in @OpenClaw. Every frontier lab should use it.
alex fazio ✈️ rome
@alxfazio
Mar 15
why is claude compaction so bad. codex compaction is basically instant. why can’t they just copy whatever oai did
2.6K
Voltropy reposted
Josh Lehman
@jlehman_
Mar 15
A common line of questions I receive: what does lossless-claw do differently than memory systems? How do the two relate? Should I use both? Here’s the lowdown: Memory systems are good for letting you search for information that’s external to your context window, which are
Peter Steinberger 🦞
@steipete
Mar 14
There's a lot of cool stuff being built around openclaw. If the stock memory feature isn't great for you, check out the qmd memory plugin! If you are annoyed that your crustacean is forgetful after compaction, give github.com/martian-engine… a try!
32K