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,

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 https://t.co/Vy8bvBNyxX ! #SwissAIWeeks

and a skyspace from James Turrell, whose work with light inspired my Vision in Art and Neuroscience class at MIT for nearly a decade. sf has a way of sneaking up on my senses with the surprisingly familiar 🫶

found two things in the de Young sculpture garden today that I had no idea were here! a beehive piece from Pierre Huyghe, who I worked with in 2022 to install a hive in simulation (along with a real one) on an island in Norway…

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! https://t.co/Or3R9E79uk

if you think data cleaning is beneath you then ngmi

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

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

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!

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 ( https://t.co/wtratbvRnF) Wednesday: Sarah (@cogconfluence) speaking at @WiMLworkshop at 10:15 and as a panelist at 11am

cf https://t.co/Xa3e7hVX26