Happy to be a small part of this colossal effort led by @zouharvi.bsky.social to reinvent the future of machine translation evaluation! 🔡 Join us in building the LTB and become a coauthor, help wanted!

⏳ The BlackboxNLP 2026 Reproducibility Challenge deadline has been extended to July 24 (AoE) ⏳ If you've been working on a robustness check, ablation, or replication of recent NLP interpretability work, you have a bit more time to get your submission in.

⏳ One week left! The submission deadline for BlackboxNLP 2026 is July 17 (AoE). If you're working on analyzing or interpreting neural networks for NLP, now's the time to get your paper in. 📍 Co-located with #EMNLP2026 in Budapest 🔗 blackboxnlp.github.io

I'd never have guessed models commit to their final answer this early, often within the first 20% of reasoning, across math/logic tasks and model families. The rest is mostly hedging that doesn't change their mind. And turns out they encode this internally, we can decode it! 🧵👇

🚨New paper led by @danielsc4.it & @saracandussio.bsky.social studying answer commitment across CoT for math & logic reasoning! Turns out, models often converge to final answers early in the CoT, then tend to "fake" hedging & re-checks - and we can tell apart mid/final guesses quite robustly! See 👇

Our @ndif-team.bsky.social was thrilled to sponsor the BlackboxNLP repro challenge! Interpretability needs more robust & generalizable findings - if you're working in this space, this should be on your radar!

It was very nice to be back in the Netherlands and EAMT to receive this prize! Thanks to everyone involved 🤗

Are you wondering if LLM interpretability results generalize, reproduce, etc.? Check out the reproducibility challenge and submit your work reproducing papers in this area: bsky.app/profile/blac...

"the new toaster says 'I Love You' when you put the toast in, and 'I'm Sorry' when it burns it. This causes some people to get angry b/c they don't think the toaster means it, and others to develop unhealthy attachments b/c they think it does. the solution is to make the toaster TRULY sorry"

We don’t always know what problems are hard for LLMs. So devs evaluate on tasks HUMANS find hard or on broad benchmarks. What if we could instead anticipate which scenarios a model will fail on—all without evaluating specific input examples? 🧵NEW PAPER by @jenniferlumeng.bsky.social

I recently spoke with Yascha Mounk about how researchers look inside AI to understand how it is thinking. Here is the podcast: writing.yaschamounk.com/p/david-bau-2

How do brains plan actions towards goals? To get at this question we studied mice navigating complex mazes as goals changed on every trial 🧵 Work with @thomasakam.bsky.social @behrenstimb.bsky.social @kristorpjensen.bsky.social now on BioRxiv: www.biorxiv.org/content/10.6...

We are starting a new, nonprofit alignment organization, ⊢ Sequent Research, bringing together researchers previously on UK AISI’s Alignment Team, Timaeus, and elsewhere to research how to align superintelligence. We are hiring! 🧵 sequent.org/launch

The New England Mechanistic Interpretability (NEMI) workshop is coming to BU on Aug. 14! Join us for talks, a panel, food, and plenty of opportunities to connect with the many great researchers in the area. Register and help spread the word!

New blog: I am worried by NLP research culture NLG and NLP are mostly much better in 2026 than when I got my PhD in 1990. Unfortunately research culture has gotten *worse” in this period, which really worries me as I retire. ehudreiter.com/2026/06/08/n...

"You're right to call me on that!" Can you catch an AI in the act of lying? Register below to enter our AI lie-detection contest. AI lies are a big problem. The frontier labs have all worked hard to fight AI deception. They all try to monitor their AIs for it.

Check out our latest work led by @veraneplenbroek.bsky.social! Conversation topics seem much better explanations for LLMs behavior over latent sociodemographic info about the user - but what does the choice of topic tell us about the speaker in the first place?

Check out our new hackathon for building the best AI lie detector on the market! A lot of interesting questions and great prizes for participants, apply early if you want in! :)

With the large influx of submissions and a faster pace of research, reproducibility is more important than ever. With this reproducibility challenge, we want to put the focus on best practices wrt. baselines🧱, ablations🌈, eval🔎 and generalizability🗺️ of interpretability!

Despite the huge inflow of researchers, much of the work in interpretability remains anecdotal. Our new repro challenge at BlackboxNLP (co-located with EMNLP 2026) aims to attract work challenging common assumptions and showing failure/success cases of popular methods. Negative results welcome!

As a computer scientist, we INVENTED the phrase "artificial intelligence." It was never exclusively yours. In both fact and fiction, AI has always been awesome, and beautiful, and, yes, problematic — and it still is.

Excellent survey on causal interpretability by @amuuueller.bsky.social and many BauLab members, don't miss it!

IMO a key skill of a good scientist is moving comfortably between the specific & general e.g., relentless in understand the nerdy details of the data (including its coding) WHILE holding onto the big picture of the hypotheses being tested with the data

Today we’re releasing EMO, a new mixture-of-experts (MoE) model trained so modular structure emerges directly from data without human-defined priors. EMO can use a small subset of its experts for a given task while keeping near full-model performance. 🧵

New paper w/ UK AISI: Millions of people now use AI to help them write and communicate. In three experiments (14k participants, 3m+ human ratings) we show that AI writing assistance systematically distorts writer personas – their perceived beliefs, personality, and identity. 🧵

🚨 Tom Griffiths has a podcast where he interviews cognitive scientists podcasts.apple.com/ca/podcast/t... This just went to the top of my list.

2026 is a whirlwind year for AI. Underlying it all is the greatest scientific mystery of our age. How does a neural network think? I talked w Oliver Whang in NYTimes Magazine, on how AI interpretability is a tangle of structure waiting to be unraveled: www.nytimes.com/2026/04/15/...

Tech industry mottos have a mixed track record. But we should hold idealists to their ideals. And we should celebrate when they come through. The Mythos non-release is a remarkable moment of conviction. Thoughts: davidbau.com/archives/20... Bravo to Anthropic's "race the top".

Mfw fiddling with probes all day but patching experiments don't pan out

Thank you for having me! Next time in person! 🤗

Calling attention to an exciting "deception detection" hackathon we're planning this summer! w @NDIF and @CadenzaLabs. Recruiting red teams now, blue teams later. Red teams, time is short: proposals due Mar 31. $10K stipend + compute, $15K finals prize. nnsight.net/blog/2026/0...

I truly believe the rapid advances in the mech interp subfield have something real to offer AI ethics researchers: A chance to look beyond the HOW of evals to the WHY, a first pass at a technical solution when we see the opportunity, a new avenue for showing failures that prove models are not gods

🧵New paper: "Lost in Backpropagation: The LM Head is a Gradient Bottleneck" The output layer of LLMs destroys 95-99% of your training signal during backpropagation, and this significantly slows down pretraining 👇

Check out David's NetHack port! "Complexity does not yield to speed. Judgment remains essential. The work of deciding what matters, of seeing what is hidden, of knowing when your own metrics are lying to you: this is the work that remains, and it is the work worth learning."

This is an important project! If you believe alignment faking is true, you should at least entertain the possibility of misalignment faking before drawing your conclusions. Especially true if researchers fishing for misaligned behaviors are the ones running the evals!

BlackboxNLP is back once again at EMNLP'26! Very happy to be part of the team again, and excited for our new reproducibility track! Check it out ⬇️

tired: meta omni-translation to 1600 low-resource languages wired: kagi translate english to mechinterp

I'm calling it DeepSeek's new 1T parameter model (V4)? The style, content, and length of the reasoning are extremely similar.

My contribution to model welfare efforts for today

This morning I happened to hang out around the Harvard med school café and all conversations I overheard were about LLMs med assistants and XAI 🫡

I want to talk about why AI-based mass surveillance is so dangerous, and why I would oppose it no matter which party or president is in office.

🔥Super excited to share our new demo website for 🪄Interpreto! 🖼️It is basically an explanation gallery showcasing attribution and concept-based explanations for classification and generation. 🎮Play with it: for-sight-ai.github.io/interpreto-d... We will keep improving it, so stay tuned!

Great wrap-up for #EVALITA2026! 🔥 Glad to have helped organize this edition and to see many interesting discussions! Great response to our task Cruciverb-IT (with Ciaccio C., @gsarti.com, Dell’Orletta F., @malvinanissim.bsky.social)! Thanks to all co-organizers and @ailc-nlp.bsky.social! #NLProc

Great release from our engineering team! A lot of the major pain points have been addressed, and this is our first step towards supporting interpretability workflows on more realistic scenarios! Check it out!

Those of us who work in AI in the US today should take a moment to think today. Do not get distracted by the circus. Instead, let us pause to think carefully about our freedoms, our rights, and our responsibilities as citizens and professionals. It is a deadly serious moment.

I'm excited to share that this paper was accepted at ICLR 2026! We show that language models encode one of the most basic ingredients of a world model: the ability to distinguish plausible from implausible states. Check out the paper for more details! See you in Rio! Paper: arxiv.org/abs/2507.12553

In this amazing multidisciplinary collaboration, we report our early experience with the @openclaw-x.bsky.social ->

Are we all Agents of Chaos in AI? (Hope not!) In recent weeks using OpenClaw has taught us a lot about this wooly new kind of autonomous software agent. Its valuable to see what @NatalieShapira, @wendlerch et al. have seen: agentsofchaos.baulab.info/

Our research report on red-teaming stateful OpenClaw agents in the BauLab is finally out! 🥳 This awesome effort was led by @natalieshapira.bsky.social and involved 6 ClawBots and 20 researchers from various institutions. Check it out ➡️ agentsofchaos.baulab.info

You can now "pip install latentlens" 🔨 It comes with: * pre-computed embeddings for several popular LLMs and VLMs * a txt file with sentences describing WordNet concepts, which we recommend as a standard corpus to get embeddings from * ... Try it out and let us know what we can improve!