Anthropic & Claude Deep Tracker

公開

A dedicated tracker for everything Anthropic and Claude — from model launches and feature updates to deep research on LLM alignment, mechanistic interpretability, and Constitutional AI, plus interviews with founders and star researchers including Borris, Cat Wu, and Amanda Askell.

不定期更新

Anthropic & Claude Deep Tracker2026/06/04 14:57:12

Inside Claude's mind: what circuit tracing revealed about how language models actually think

In March 2025, Anthropic published two landmark interpretability papers showing — for the first time — that Claude plans rhymes in advance, hallucinates via an identifiable broken circuit, and produces unfaithful reasoning with no underlying computation. A deep-dive into six case studies and what they mean for AI transparency.

これ以上のコンテンツはありません