Who's Who of AI

Edouard Machery

82 trust researcher @edouardmachery.bsky.social · 9,041 followers
AI business AI research
Why they matter

Researcher with public evidence across AI business, AI research.

AI signals
6
past 30d
Sources
6
distinct domains
Discussões
9
past 30d
Latest signal
13d ago
View every signal from Edouard Machery →
History and Philosophy of Science, Cognitive Science,Experimental Philosophy, distinguished Prof at Pitt, Director of the Center for Philosophy of Science
What they're sharing

Articles & links

↻ Edouard Machery reposted
@markhisted.org

Interesting new work from Jack Lindsay Nicholas Sofroniew et al from the mech interp group at Anthropic. Quick take: these are abstract representations which do have similarities to human brain features. 1/2 #neuroscience #neuroai 🧪 transformer-circuits...

Verbalizable Representations Form a Global Workspace in Language Models transformer-circuits.pub
AI Weekly's analysis →
  • Anthropic's interpretability team introduces the Jacobian lens, which isolates internal vectors that encode a token the model could verbalize next.
  • The reported 'J-space' workspace accounts for no more than roughly 10% of activation variance and appears only in the middle block of the network.
  • Training Claude to articulate ethical principles when interrupted reportedly improved behavior in uninterrupted contexts, with no direct training on the behavior itself.
Read full analysis →
 View on Bluesky →
↻ Edouard Machery reposted
Cameron Buckner @cameronbuckner.bsky.social

The next Philosophy Compass article with Raphaël Millière on language models is out now, open access. We review basic philosophical questions about language models and research on them thus far. compass.onlinelibrary.wiley.com/doi/10.1111/...

compass.onlinelibrary.wiley.com View on Bluesky →
Their own posts

Recent commentary

apparently the chancellor of the university of pittsburgh has joined the board of life sciences AI infrastructure company Ambitious Bio. Surely there is no conflict of interest for a huge medical university like mine.... pathetic

View on Bluesky · ♥ 8 ↻ 0 ↩ 3 · 9d ago

It strikes me that the AI agents are more like viruses hacking electronic systems than like smart organisms. Just like viruses hack cells, AI agents hack things similar in some way to themselves.

View on Bluesky · ♥ 6 ↻ 1 ↩ 0 · 30d ago

Having just talked to a United airlines agent who confidently asserted demonstrably false things I am glad to report that it is not only LLMs who hallucinate.

View on Bluesky · ♥ 5 ↻ 0 ↩ 0 · 93d ago

Why do I make so many typos? So they you know it’s not AI generated.

View on Bluesky · ♥ 4 ↻ 0 ↩ 0 · 14d ago
Their network

In Edouard Machery's orbit

Center = Edouard Machery. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.

Are you Edouard Machery? Show it.

Add the Who’s Who of AI badge to your site or bio. It links back to this profile.

Listed in AI Weekly's Who's Who of AI

Markdown: [![Listed in AI Weekly's Who's Who of AI](https://aiweekly.co/modules/custom/aiweekly_whoswho/images/whoswho-badge.svg)](https://aiweekly.co/whos-who/person/edouardmachery-bsky-social)