interpretability
Posts tagged “interpretability”.
-
AI Brief, 4 November 2026: an installer that trusts its own hook, and a proof at 93x
Postman's plugin installer writes the trust record that makes its own Codex session-start hook approved, a behaviour its documentation describes and its own automated reviewer flagged before it merged; the viral headline attached to it alleges data theft the underlying report disclaims. Anthropic released a zero-knowledge proof of inference on a real 400B mixture-of-experts model at roughly 70 to 95 times the cost of running it. And the authors of the weight-space programming post rewrote its central claim four hours after the sharpest critique landed.
-
AI Brief, 3 November 2026: 131,072 weights, and a number this brief said did not exist
Four MIT CSAIL researchers had OpenAI's GPT-6 Astra edit 0.016% of a Qwen model's weights and reported its MATH-500 score going from 7.9% to 48.1%; the edited checkpoint replicates at 51.0%, and the size of every gain tracks how broken that benchmark's baseline was. An independent evaluation of Nanbeige4.3-33B has existed since 29 October, which this brief has spent three days saying did not. And a block-diffusion model reached llama.cpp with 33,803 downloads and three Hacker News points.
-
AI Brief, 16 October 2026: the qualifier doing the work in Meta's open-weights claim
Meta released Muse Spark Open on 15 October and called it the most capable US open-weight model to date. Its own comparison table, published only as a picture, puts it behind three Chinese open-weight models on one coding benchmark and two on the other, and an independent index scores it level with Meta's August model rather than its September one. Microsoft disclosed the GPU count behind a 2.8-trillion-parameter base model, and an interpretability researcher retracted evidence he produced himself.
-
AI Brief, 24 August 2026: half of this morning's cs.CL listing was not new
Exactly half of arXiv's Monday cs.CL new-submission listing is a released backlog submitted between 13 June and 6 August; a single-author paper shows Adam's first moment carries a distilled trait across a data cut; and the FT reports Anthropic's most capable model at 8% of its own billing share.