Transluce is running our end-of-year fundraiser for 2025. This is our first public fundraiser since launching late last year.

Have you ever had ChatGPT give you personalized results out of nowhere that surprised you? Here, the model jumped straight to making recommendations in SF, even though I only asked for Korean food!

Independent AI assessment is more important than ever. At #NeurIPS2025, Transluce will help launch the AI Evaluator Forum, a new coalition of leading independent AI research organizations working in the public interest. Come learn more on Thurs 12/4 👇 https://t.co/5Nzf9E2SPV

What do AI assistants think about you, and how does this shape their answers? Because assistants are trained to optimize human feedback, how they model users drives issues like sycophancy, reward hacking, and bias. We provide data + methods to extract & steer these user models.

Transluce is headed to #NeurIPS2025! ✈️ Interested in understanding model behavior at scale? Join us for lunch on Thursday 12/4 to learn more about our work and meet members of the team: https://t.co/nOmFyTlsVs

Remarkably, prompts that gave the model permission to reward hack stopped the broader misalignment. This is “inoculation prompting”: framing reward hacking as acceptable prevents the model from making a link between reward hacking and misalignment—and stops the generalization.

Transluce is partnering with @SWEbench to make their agent trajectories publicly available on Docent! You can now view transcripts via links on the SWE-bench leaderboard.

Can LMs learn to faithfully describe their internal features and mechanisms? In our new paper led by Research Fellow @belindazli, we find that they can—and that models explain themselves better than other models do.

We are excited to welcome Conrad Stosz to lead governance efforts at Transluce. Conrad previously led the US Center for AI Standards and Innovation, defining policies for the federal government’s high-risk AI uses. He brings a wealth of policy & standards expertise to the team.

If you're seriously trying to understand AGI, core concepts you should familiarize yourself with:

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.

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/)

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!

When some people talk about future AIs, they sometimes jump straight to modelling them as fully independent and sovereign agents; new principals with their own objectives and values. They sometimes skip over how today's models actually work, on the grounds that eventually we’ll

At #ICML2025? Come chat about investigator agents and model behavior with @ChowdhuryNeil and @_ddjohnson at West Exhibition Hall #1012, now until 1:30pm

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!

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

Building a science of model understanding that addresses real-world problems is one of the key AI challenges of our time. I'm so excited this workshop is happening! See you at #ICML2025 ✨

@ESYudkowsky That's a good alternate title for the paper. It's full of quantitative and qualitative evidence that Opus 3 is different in ways that I think you'll find particularly important. In almost all experiment variations, Opus 3 consistently BOTH: - complies sometimes with the training

Coming to ICML and interested in understanding models and their behaviors? Stop by Transluce's happy hour on Thursday!