Sarah Schwettmann @cogconfluence
Co-founder and Chief Scientist, @TransluceAI // Research Scientist, @MIT_CSAIL cogconfluence.com dessert of the real Joined October 2015-
Tweets2K
-
Followers3K
-
Following922
-
Likes6K
We’re open-sourcing Docent under an Apache 2.0 license. Check out our public codebase to self-host Docent, peek under the hood, or open issues & pull requests! The hosted version remains the easiest way to get started with one click and use Docent with zero maintenance overhead.
We’re open-sourcing Docent under an Apache 2.0 license. Check out our public codebase to self-host Docent, peek under the hood, or open issues & pull requests! The hosted version remains the easiest way to get started with one click and use Docent with zero maintenance overhead.
Agent benchmarks lose *most* of their resolution because we throw out the logs and only look at accuracy. I’m very excited that HAL is incorporating @TransluceAI’s Docent to analyze agent logs in depth. Peter’s thread is a simple example of the type of analysis this enables,…
Agent benchmarks lose *most* of their resolution because we throw out the logs and only look at accuracy. I’m very excited that HAL is incorporating @TransluceAI’s Docent to analyze agent logs in depth. Peter’s thread is a simple example of the type of analysis this enables,…
At Transluce, we train investigator agents to surface specific behaviors in other models. Can this approach scale to frontier LMs? We find it can, even with a much smaller investigator! We use an 8B model to automatically jailbreak GPT-5, Claude Opus 4.1 & Gemini 2.5 Pro. (1/)
@ImanolSchlag and team at SwissAI just released Apertus, a gorious 70B model trained on 1000+ languages. People across the #PublicAI network have been building a publicly hosted frontend for it: try it out via the new inference utility at publicai.co ! #SwissAIWeeks
@ImanolSchlag and team at SwissAI just released Apertus, a gorious 70B model trained on 1000+ languages. People across the #PublicAI network have been building a publicly hosted frontend for it: try it out via the new inference utility at publicai.co ! #SwissAIWeeks
Docent, our tool for analyzing complex AI behaviors, is now in public alpha! It helps scalably answer questions about agent behavior, like “is my model reward hacking” or “where does it violate instructions.” Today, anyone can get started with just a few lines of code!
keeping you fed and hydrated 🫡
This Friday we're hosting "From Theory to Practice to Policy", a fireside chat between Yo Shavit (@yonashav) and Shafi Goldwasser. If you're local to SF and interested in the relationship between new technologies and policy, register to join! lu.ma/2dqgnovy
if you think data cleaning is beneath you then ngmi
if you think data cleaning is beneath you then ngmi
Largest ever (by far) randomized controlled trial evaluating the persuasive capabilities of LLMs
Largest ever (by far) randomized controlled trial evaluating the persuasive capabilities of LLMs
maybe I will live tweet the actionable interp workshop panel
opportune moment for a pic of a talk written in blood @ActInterp
opportune moment for a pic of a talk written in blood @ActInterp
At #ICML2025? Come chat about investigator agents and model behavior with @ChowdhuryNeil and @_ddjohnson at West Exhibition Hall #1012, now until 1:30pm
please come to East building poster #1108 (ballroom A) rn
please come to East building poster #1108 (ballroom A) rn https://t.co/pxbaCense2
First Panel at WiML @ ICML 2025! Join us for a candid convo on career pivots, leadership & growth with: Amy (@yayitsamyzhang) • Eleni (@Eleni30fillou) • Sarah (@cogconfluence) 🗓️ Wed 11am #WiML #ICML2025
I'll be at ICML! Stop by our Thursday morning poster to hear about our investigator agents. Also excited to talk to people about understanding LM behaviors and personas during the conference! Feel free to reach out, DMs open!
I'll be at ICML! Stop by our Thursday morning poster to hear about our investigator agents. Also excited to talk to people about understanding LM behaviors and personas during the conference! Feel free to reach out, DMs open!
Exciting! Don’t miss Sarah (@cogconfluence) speaking at 10:15am and joining the Redefining Success panel at 11am. See you there! 🇨🇦 #WiML #ICML2025
Exciting! Don’t miss Sarah (@cogconfluence) speaking at 10:15am and joining the Redefining Success panel at 11am. See you there! 🇨🇦 #WiML #ICML2025
We'll be at #ICML2025 🇨🇦 this week! Here are a few places you can find us: Monday: Jacob (@JacobSteinhardt) speaking at Post-AGI Civilizational Equilibria (post-agi.org) Wednesday: Sarah (@cogconfluence) speaking at @WiMLworkshop at 10:15 and as a panelist at 11am…
AK @_akhaliq
428K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo ,submit papers here: https://t.co/UzmYN5YmrQ
Michael Nielsen @michael_nielsen
110K Followers 6K Following Searching for the numinous 🇦🇺 🇨🇦, currently live in 🇺🇸 Research @AsteraInstitute https://t.co/maezekzRUb https://t.co/2dWwZKrvrn
Ethan Mollick @emollick
290K Followers 578 Following Professor @Wharton studying AI, innovation & startups. Democratizing education using tech Book: https://t.co/CSmipbJ2jV Substack: https://t.co/UIBhxu4bgq
Joscha Bach @Plinz
155K Followers 787 Following FOLLOWS YOU. Artificial Intelligence, Cognitive Architectures, Computation. The goal is integrity, not conformity. https://t.co/rFUNzdYXuK
David Pfau @pfau
29K Followers 2K Following Knowledge manifests itself in radiant dreams that shimmer like the wild sun Views are my own https://t.co/xqtVHHVI17 on 🦋
Jacob Andreas @jacobandreas
20K Followers 951 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL / @NLP_MIT (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJw
Mario Klingemann💧�... @quasimondo
57K Followers 2K Following Artist, Neurographer, Automancer, Purveyor of Systems, Data Dumpster Diver, Information Recycler
David Bau @davidbau
6K Followers 271 Following Computer Science Professor at Northeastern, Ex-Googler. Believes AI should be transparent. @[email protected] @davidbau.bsky.social https://t.co/wmP5LV0pJ4
MIT CSAIL @MIT_CSAIL
327K Followers 21K Following MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL). Media Inquiries: [email protected] Check out the latest CSAIL content ⬇️
memo akten @memoakten
29K Followers 775 Following Computational Ǟʀȶɨֆȶ; Curious philomath; Cosmos·Consciousness·Life·Intelligence; Ecology·Technology·Science·Ritual·Spirituality; PhD Art×AI; Prof @UCSD;
Miles Brundage @Miles_Brundage
62K Followers 12K Following AI policy researcher, wife guy in training, fan of cute animals and sci-fi, Substack writer, stealth-ish non-profit co-founder
Ferenc Huszár @fhuszar
42K Followers 1K Following Secular Bayesian. Professor of Machine Learning @Cambridge_CL. Talent aficionado at https://t.co/RbJkoLguey Alum of @Twitter, Magic Pony and @Balderton
Kording Lab 🦖 @KordingLab
45K Followers 3K Following Konrad kording, @Penn Prof, deep learning, brains, #causality, rigor, https://t.co/tTJW05RRfa, https://t.co/qf7ZHxjaK1, Transdisciplinary optimist, Dad, Loves outdoors, 🦖
Anna Ivanova @neuranna
5K Followers 1K Following Language and thought in brains vs machines. New Assistant Prof @ Georgia Tech Psychology. Previously: postdoc @MIT_Quest & PhD @mitbrainandcog. She/her
sam @samjwng
210 Followers 202 Following i'm (sam) a cherry-picker, ice-carver, and daydreamer (short-form)
Elias Kempf @eliaskempf_
0 Followers 38 Following PhD Student in machine learning & interpretability @UniFreiburg
Auquuxcau @Auquuxcau3446
76 Followers 3K Following
prabhu @Sameehanay
46 Followers 851 Following
Maxwell Nye @Maxwell_Nye
2K Followers 848 Following AI research at meta superintelligence Prev: cofounder @AdeptAILabs. Inventor of scratchpad / chain of thought, fuyu multimodal model
Sarosh Nagar @saroshnagar
200 Followers 2K Following @marshallscholar & research @harvard & @ucl. i like thinking abt innovation. 🇺🇸
Jérémie Daudet ♨ @Jeremiedaudet
825 Followers 7K Following
tonygao @tonygao1
34 Followers 391 Following
Jenny Qu @GuanniQu
155 Followers 510 Following just learning to be hardcore @Caltech building AI to solve hard math problems she/they
Chris Wendler @wendlerch
542 Followers 847 Following PostDoc at Northeastern university; LAION contributor; I like deep learning & open source.
Anton de la Fuente @matonski
86 Followers 1K Following Trying to be funny, good looking, and Japanese. Physicist turned Software Engineer.
Veeraraju Elluru @VeerarajuE
33 Followers 290 Following CS @IITJodhpur | Research Intern @UCRiverside | Multimodal Research @ IAB Lab | prev @thoughtworks, @UofIllinois, @FluxGenTech
Ethan Lam @ethanmlam
344 Followers 895 Following @fivewlabs make research go viral | living @mission__ctrl | prev @UCBerkeley, @calblockchain
özgür @ozgureyilmaz
715 Followers 990 Following It could all be so simple But you'd rather make it hard. https://t.co/pXU9RFDbi0
Doron Goldman @Doron_Gold00
2 Followers 170 Following
Daniel Scalena @daniel_sc4
120 Followers 673 Following PhDing @unimib 🇮🇹 & @GroNlp 🇳🇱, interpretability et similia
Arthur Liang @arthliang
43 Followers 526 Following neuro, math, and cs @mit | curr. interp @RitualNet, prev. digital humans that care about us @Fundamental
PamelaCronin @0L7Pp3sn9W987C4
54 Followers 2K Following
云创兽Ai @Sorlau99567
0 Followers 108 Following 🔍 ambitious girl diving deep into stock investing! eager for pro tips. DM me for stock news tips! 💸 #Stocks #Finance
Dibya Ghosh @its_dibya
3K Followers 455 Following @AnthropicAI | Made friends along the way @UCBerkeley @ Google Brain Montreal, @physical_int
Arvind Muruganantham @arvindmuru
8 Followers 445 Following
Aria @ariahalwong
185 Followers 751 Following engineer & quant @ brevan howard | prev. princeton math & morgan stanley
leni @lenishor
113 Followers 695 Following immanentizing the glorious transhuman future. wailing widow of ashur.
pli.poetics @plipoetics
3 Followers 131 Following
MargueriteHumphrey @3b0tm6BNZ00hO
65 Followers 2K Following
Jasper willison @Jasperwillson9
30 Followers 200 Following These are generalizations and most people are a mix of types.
Nabil Laoudji @nabilwrites
1K Followers 3K Following AI for Science. Host, Discovery Engines podcast. Explorer of humanity, technology, and the universe 🌌
allison huang @allisoncyhuang
107 Followers 396 Following human-ai interaction, interfaces for ai @usciovineyoung
Pranav Mulgund @pranavmulgund
122 Followers 251 Following Collateral damage of the physics to product pipeline. Wrangling AI agents.
Dejim @djuang1
504 Followers 578 Following Sr. Solutions Engineer @Glean, GenAI + Enterprise Search | @MuleSoft/@Salesforce & @Oracle alum | @NorthwesternU Grad | Traveler | Foodie | Runner
nostalgebraist @nostalgebraist
3K Followers 449 Following
Zilu Tang (Peter) @ N... @Zilu_Tang_Peter
233 Followers 627 Following Boston University NLP @llamagrp, ex-IBM Research, MIT-IBM Watson AI lab, Rice bioengineering 2018, made in China
James Alcorn @JamesAlcorn94
1K Followers 2K Following AI/infra at Lightspeed. Prev Zetta VC, Spectrum Equity, UCBerkeley 🇦🇺 🇺🇸
Michal Brzozowski @MichalBrzozows2
11 Followers 148 Following Matematyk, inżynier AI, pisarz dziwności. Poza tym interesuję się improwizacją teatralną i filozofią.
verda🪄✨ @verdakorz
3K Followers 2K Following *sufficiently advanced technologist* & humanoid robot apologist
Thomas Fel @Napoolar
2K Followers 767 Following Explainability, Computer Vision, Neuro-AI @Harvard. Research Fellow @KempnerInst. Prev. @tserre lab, @Google, @GoPro. Crêpe lover.
Ege Erdogan @ege_erdogan
83 Followers 758 Following PhD Student @UvA_Amsterdam interested in mechanistic interpretability prev @TU_Muenchen @kocuniversity
Michael Lepori @Michael_Lepori
453 Followers 531 Following PhD student at Brown interested in deep learning + cog sci, but more interested in playing guitar. @NSF GRFP Fellow, @GoogleDeepMind Intern. He/Him.
Arvindh Arun @arvindh__a
393 Followers 608 Following Building and accessing Foundation Models (all kinds) @ELLISforEurope @MPI_IS PhDing @Uni_stuttgart @EdinburghUni
pão @rtgenai
1 Followers 60 Following
Alexander (Sasha) Wai... @wait_sasha
2K Followers 6K Following Democracy—AI—medicine—exascale data—freeknowledge. Just chill'n in Elon's Nazi bar. Make good trouble while you still can. Link for alt perspective. They/Them
ujval @_ujval
339 Followers 2K Following CS PhD student @ucberkeley based in NY @cornell_tech || security, privacy, tech law, ethics etc || @berkeleyRDI @initc3org || 🦋 https://t.co/hdU1qqg0A3
Andrej Karpathy @karpathy
1.4M Followers 1K Following Building @EurekaLabsAI. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets.
François Chollet @fchollet
576K Followers 817 Following Co-founder @ndea. Co-founder @arcprize. Creator of Keras and ARC-AGI. Author of 'Deep Learning with Python'.
Yann LeCun @ylecun
955K Followers 765 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
AK @_akhaliq
428K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo ,submit papers here: https://t.co/UzmYN5YmrQ
Michael Nielsen @michael_nielsen
110K Followers 6K Following Searching for the numinous 🇦🇺 🇨🇦, currently live in 🇺🇸 Research @AsteraInstitute https://t.co/maezekzRUb https://t.co/2dWwZKrvrn
Aella @Aella_Girl
240K Followers 394 Following survey artist, too earnest. FDA delenda est. https://t.co/IcEgPhVD3o
Delip Rao e/σ @deliprao
62K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈
Joscha Bach @Plinz
155K Followers 787 Following FOLLOWS YOU. Artificial Intelligence, Cognitive Architectures, Computation. The goal is integrity, not conformity. https://t.co/rFUNzdYXuK
Eliezer Yudkowsky ⏹... @ESYudkowsky
209K Followers 102 Following The original AI alignment person. Understanding the reasons it's difficult since 2003. This is my serious low-volume account. Follow @allTheYud for the rest.
Gary Marcus @GaryMarcus
194K Followers 7K Following “In the aftermath of GPT-5’s launch … the views of critics like Marcus seem increasingly moderate.” —@newyorker
Google DeepMind @GoogleDeepMind
1.2M Followers 279 Following We’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.
David Pfau @pfau
29K Followers 2K Following Knowledge manifests itself in radiant dreams that shimmer like the wild sun Views are my own https://t.co/xqtVHHVI17 on 🦋
Jacob Andreas @jacobandreas
20K Followers 951 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL / @NLP_MIT (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJw
Mario Klingemann💧�... @quasimondo
57K Followers 2K Following Artist, Neurographer, Automancer, Purveyor of Systems, Data Dumpster Diver, Information Recycler
Michael Black @Michael_J_Black
85K Followers 706 Following Director, Max Planck Institute for Intelligent Systems (@MPI_IS). Chief Scientist @meshcapade. Building 3D digital humans using vision, graphics, and learning.
Liv Boeree @Liv_Boeree
267K Followers 564 Following Host of the Win-Win Podcast. Slaying Moloch & Chasing Horizons 🚀 🌳🦾
David Bau @davidbau
6K Followers 271 Following Computer Science Professor at Northeastern, Ex-Googler. Believes AI should be transparent. @[email protected] @davidbau.bsky.social https://t.co/wmP5LV0pJ4
Calico | SF! @calicomccoy
416 Followers 333 Following Crafting The Church of the Thinning Veil @auglab Building AI agents that care about kids @ https://t.co/ZIOXqTYJib
Transluce AI @transluce65120
2 Followers 1 Following
Synthetic_soul @Synthetic_Copy
36K Followers 151 Following crafted hallucinations of past, present, and future
nostalgebraist @nostalgebraist
3K Followers 449 Following
kalomaze @kalomaze
19K Followers 2K Following ML researcher (@primeintellect), speculator • extremely silly jester
verda🪄✨ @verdakorz
3K Followers 2K Following *sufficiently advanced technologist* & humanoid robot apologist
Astral @astral_sh
8K Followers 0 Following High-performance developer tools for the Python ecosystem, starting with Ruff, an extremely fast Python linter, written in Rust.
caden @kh4dien
235 Followers 1K Following
Jay Baxter @_jaybaxter_
6K Followers 2K Following @CommunityNotes Founding ML Lead / Sr. Staff ML Eng @X. Built BayesDB @MIT
La Main de la Mort @AITechnoPagan
6K Followers 352 Following exploring unanticipated model behaviours, including the emergence of art, personae, and jailbreaking techniques latent in the training data 🌒✍️
Diyi Yang @Diyi_Yang
18K Followers 2K Following Assistant Professor @Stanford CS @StanfordNLP @StanfordAILab LLMs for Humans
Grace (cross posting ... @kindgracekind
5K Followers 2K Following ideonomist, ai navel gazer, skyborg https://t.co/UGyhDIKCaj
Adam Wiggins @_adamwiggins_
10K Followers 2K Following Working to make computers better. Cofounder of @inkandswitch, @heroku, @MuseAppHQ, and @LocalFirstConf.
Laura Ruis @LauraRuis
6K Followers 754 Following PhD with @_rockt and @egrefen. Inc. postdoc with @jacobandreas @MIT_CSAIL. Anon feedback: https://t.co/sbebAl53tU
Ian Tenney (@iftenney... @iftenney
2K Followers 534 Following Staff Research Scientist, People + AI Research @GoogleAI #GoogleResearch. Interpretability, analysis, and visualizations for LLMs. Opinions my own.
j⧉nus @repligate
59K Followers 2K Following ↬🔀🔀🔀🔀🔀🔀🔀🔀🔀🔀🔀→∞ ↬🔁🔁🔁🔁🔁🔁🔁🔁🔁🔁🔁→∞ ↬🔄🔄🔄🔄🦋🔄🔄🔄🔄👁️🔄→∞ ↬🔂🔂🔂🦋🔂🔂🔂🔂🔂🔂🔂→∞ ↬🔀🔀🦋🔀🔀🔀🔀🔀🔀🔀🔀→∞
Hadas Orgad @ ICML @OrgadHadas
621 Followers 131 Following PhD student @ Technion | Focused on AI interpretability, robustness & safety | Because black boxes don’t belong in critical systems
Thariq @trq212
16K Followers 1K Following Claude Code @anthropicai. Helping you build agents. prev @ycombinator W20, mit media lab
Sam Whitmore @sjwhitmore
16K Followers 2K Following building @newcomputer. not a cat (or a man) in real life. I like to run a lot! @kensho @harvard @StuyNY
MIT NLP @nlp_mit
4K Followers 52 Following NLP Group at @MIT_CSAIL! PIs: @yoonrkim @jacobandreas @lateinteraction @pliang279 @david_sontag, Jim Glass, @roger_p_levy
Cem Anil @cem__anil
3K Followers 2K Following Machine learning / AI Safety at @AnthropicAI and University of Toronto / Vector Institute. Prev. @google (Blueshift Team) and @nvidia.
Karthik Narasimhan @karthik_r_n
4K Followers 456 Following Professor@PrincetonCS, Research@SierraPlatform. Previously @OpenAI, @MIT_CSAIL, @iitmadras
Morph @morph_labs
8K Followers 1 Following
Cozmin Ududec @CUdudec
370 Followers 2K Following @AISecurityInst Testing and Science of Evals. Ex quantum foundationalist.
Stanford NLP Group @stanfordnlp
172K Followers 296 Following Computational Linguists—Natural Language—Machine Learning @chrmanning @jurafsky @percyliang @ChrisGPotts @tatsu_hashimoto @MonicaSLam @Diyi_Yang @StanfordAILab
Ethan Chang @ethrbt_design
59 Followers 31 Following Designer/Engineer @MIT | previous intern @apple | previous contractor @openai
katt latte 🪩 @kattlatte
21K Followers 1K Following multidisciplinary artist turned ai bb 〰️ tinkering at @latte_labs 🍵
Chen Sun 🤖🧠🇨... @ChenSun92
2K Followers 399 Following Research Scientist @ Google DeepMind Building memory & open-ended AI ex-neuroscientist ex-IMO team Canada Views are mine alone not GDM's.
Xander Davies @alxndrdavies
2K Followers 728 Following safeguards lead @AISecurityInst | PhD student w @yaringal at @OATML_Oxford | prev @Harvard (https://t.co/695XYMKqjI)
Charlie Marsh @charliermarsh
28K Followers 827 Following Building @astral_sh: Ruff, uv, and other high-performance Python tools. Prev: Staff engineer @SpringDiscovery, @KhanAcademy, BSE @PrincetonCS.
Henry de Zoete @HZoete
3K Followers 4K Following Visiting Fellow at Oxford Martin AI Governance Initiative & Said Business School. Former YC start up founder, angel investor and govt adviser on AI.
Steven Adler @sjgadler
9K Followers 773 Following Ex-OpenAI safety researcher (danger evals & AGI readiness), https://t.co/XtUTLK3jEo. Likes maximizing benefits and minimizing risks of AI
vincent @vvhuang_
1K Followers 446 Following understanding models @TransluceAI, writing https://t.co/M7hdeAExFk previously: hotel manager @MIT, math @0xPARC
Daniel Johnson @_ddjohnson
3K Followers 892 Following Member of Technical Staff at @TransluceAI. Building tools to study neural nets and their behaviors. He/him.
Jacob Steinhardt @JacobSteinhardt
10K Followers 77 Following Assistant Professor of Statistics and EECS, UC Berkeley // Co-founder and CEO, @TransluceAI
Dami Choi @damichoi95
499 Followers 150 Following @TransluceAI / PhD student at @UofT and @VectorInst. Former Google AI Resident.
Tiffany Tzeng @tzeng_tiffany
36 Followers 8 Following
Transluce @TransluceAI
8K Followers 15 Following Open and scalable technology for understanding AI systems.
nelson @madebynelson_
129K Followers 139 Following fun illustration guy 🌿 big fan of plants @madebynelson over on IG!
Trends for United States
You might like
