Anthropic publishes circuit-tracing study of Claude 3.5 Haiku's internal biology
burny_tech · x · 2026-10-27
Anthropic released 'On the Biology of a Large Language Model' on the Transformer Circuits Thread (Jack Lindsey, Chris Olah, et al.), reverse-engineering Claude 3.5 Haiku's internal mechanisms via circuit tracing. Case studies span multi-step reasoning, rhyme planning in poems, multilingual circuits, addition, medical diagnoses, entity recognition and hallucinations, refusals, the life of a jailbreak, chain-of-thought faithfulness, and hidden misaligned goals. The authors frame understanding LLMs as analogous to biology: simple training algorithms yield intricately complex mechanisms.
More from Research
- LLM rewrites a physics paper into a clearer 12-page explainer — correctness unverified — thomasahle · 2026-10-27
- OpenAI's new math results accused of scooping community mathematician's Yang-Mills work — burny_tech · 2026-10-27
- NYC Reliable AI Meetup on Synthetic Data Set for Nov 16 with NYU's Gautam Kamath — karen_ullrich · 2026-10-27
- Meta's InteractiveWorld Benchmark Shows MLLMs Still Far from Reliable Physical Assistants — meta · 2026-10-27
- Xiaomi and Wuhan University Release WorldCast for Large-Angle Camera-Controlled Character Video — Lei Cao · 2026-10-27
- UCL's CLE Benchmark Finds Best Frontier LLM Agent Clears Only 47.7% of Levels — UniversityCollegeLondon · 2026-10-27