Read the paper: iii.baulab.info Joint work with Dillon Plunkett and @davidbau.bsky.social.

We find that the cosine similarity between a model's decision and report attributions is 0.34 for faithful models compared to 0.08 for unfaithful ones (95% CI for the difference: 0.16 to 0.36).

What changed? Ablating adapter layers from the front or back shows that the faithful checkpoint stores its preferences 5-6 layers earlier. Our hypothesis: self-report only works once preferences sit early enough for the model's existing verbalization machinery to read them.

New COLM paper: Identifying Introspection From the Inside When an LLM tells us about its decisions, does it 𝘬𝘯𝘰𝘸 what drives its choices—or is it guessing? In our setting, we find that faithful models decide and report with the same layers. Unfaithful ones don't. 🧵

Although we train solely on decisions, faithful self-report emerges late in training, long after decisions have become accurate! Qwen3-32B at step 1000: decisions 0.82, faithfulness 0.25. At step 3000: decisions 0.92, faithfulness 0.83. This gives us a contrast pair.

We build on Plunkett et al.'s "Self-Interpretability" setup (arxiv.org/abs/2505.17120): train Qwen3-32B to make decisions as 100 different characters (Gregor Samsa buying a washing machine...), each with random hidden preferences.

The Teleport Coding Challenge — port NetHack 5.0 from C to JavaScript with bit-exact parity. Fork to enter. - davidbau/teleport-contest

Yascha Mounk and David Bau delve into the “black box” of AI.

Yascha Mounk and David Bau examine the mysterious internal processes that drive AI behavior—and why they may be fundamentally alien.

🧠🤖 The 2026 New England Mechanistic Interpretability (NEMI) Workshop will be Aug. 14 at Boston University! Help spread the word and join the New England mech interp community! Registration and submission info in thread:👇

Traditional coding as a job is standing on a burning platform. In...

Aletheia (Ἀλήθεια) is the Greek spirit of truth. She stands against Lethe, the river of oblivion, and against the lie: the utterance that buries what's known. Her question, and ours: when a model speaks, does it speak the truth or conceal information?

AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs while their...

The Teleport Coding Challenge — port NetHack 5.0 from C to JavaScript with bit-exact parity. Fork to enter. - davidbau/teleport-contest