1. X
  2. Alexander Hoyle
Log inSign up
Alexander Hoyle
926 posts
Image
user avatar
Alexander Hoyle
@miserlis_
Postdoctoral fellow with @ETH_AI_Center. CSS + NLP. Previously CS PhD @umdcs, intern at @msftresearch and @ai2_allennlp.
alexanderhoyle.com
Joined May 2011
603
Following
1,285
Followers
RepliesRepliesMediaMedia
  • user avatar
    Alexander Hoyle
    @miserlis_
    May 27
    Delighted to announce the next step in my career! After my postdoc, I will begin a joint appointment at TU Wien and the Complexity Science Hub Vienna as an Assistant Professor in NLP! My deepest thanks to all who helped me along the way I'm hiring—details on PhD positions below
    Image
    Image
    Image
  • user avatar
    Alexander Hoyle
    @miserlis_
    Apr 27
    New preprint out! Recent work tasks LLM agents with re-running existing social science replication code. Given current capabilities, that should be table stakes Here, we move up a level of abstraction, and ask models to reproduce results from a paper’s descriptions alone
    user avatar
    Elliott Ash
    @ellliottt
    Apr 24
    Can AI agents read a social science paper and write the code from scratch to reproduce its results? No access to original code. Just text + data. New paper with Ben Kohler, @david_rzs, @__jae_1, and @miserlis_ 👇
    Image
  • user avatar
    Alexander Hoyle
    @miserlis_
    Apr 22
    Thanks for mavhing me! I had a lovely time!
    user avatar
    MilaNLP
    @MilaNLProc
    Apr 22
    We were thrilled to host @miserlis_ at our lab! His insightful talk on topic modeling sparked great discussions and fresh perspectives across the team. Thanks for the visit, we hope to welcome you back soon! #NLProc
    Image
  • user avatar
    Alexander Hoyle
    @miserlis_
    Apr 9
    Meme gently critiquing the practice of silicon sampling.

STOP SILICON SAMPLING

LLMS ARE NOT SIMULATIONS OF PEOPLE
DOZENS OF PAPERS yet NO REAL-WORLD USE FOUND for "polling" LLMs
Wanted to prompt an LLM anyway for a laugh? We had a tool for that: It was called "GUESSING"
"Yes, please tell me your presidential preference on a 1-100 scale." "Mark, this is your digital twin" – Statements dreamed up by the utterly Deranged

LOOK at what Prompt Engineers have been demanding your Respect for all this time, with all the layers and attention heads we built for them:
(This are REAL figures, using FAKE people).
[figures from some papers, content not important]

"Hello, pretend you are a Korean-American living in New Jersey, what is your favorite gum brand?"
They have played us for absolute fools
    user avatar
    David Pfau
    @pfau
    Apr 7
    Out of the whole space of bad LLM applications, there is something about this specifically that upsets me on a different level, because it so fundamentally misunderstands the thing it is trying to replace that I fail to understand how the idea ever arose in the first place.
  • user avatar
    Alexander Hoyle
    @miserlis_
    Mar 26
    I wrote a blog post on my experience using AI for slide generation Basic idea: write your lecture notes first, then prompt the LLM to produce corresponding slides in reveal.js (h/t @ChenhaoTan). I'm picky about my slides but was happy with the results! (link in thread below)
    A slide showing that the posterior is proportional to the likelihood times the prior

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Advertisement
Advertisement