Hacker News
- Circuit Tracing: Revealing Computational Graphs in Language Models (Anthropic) https://transformer-circuits.pub/2025/attribution-graphs/methods.html 27 comments
Linking pages
- Anthropic scientists expose how AI actually 'thinks' — and discover it secretly plans ahead and sometimes lies | VentureBeat https://venturebeat.com/ai/anthropic-scientists-expose-how-ai-actually-thinks-and-discover-it-secretly-plans-ahead-and-sometimes-lies/ 286 comments
- The Parrot is Dead - by Jack Wiseman - Inference Magazine https://inferencemagazine.substack.com/p/the-parrot-is-dead 102 comments
- Why do LLMs make stuff up? New research peers under the hood. - Ars Technica https://arstechnica.com/ai/2025/03/why-do-llms-make-stuff-up-new-research-peers-under-the-hood/ 1 comment
- What Anthropic Researchers Found After Reading Claude’s ‘Mind’ Surprised Them https://singularityhub.com/2025/03/28/what-anthropic-researchers-found-after-reading-claudes-mind-surprised-them/ 0 comments
Related searches:
Search whole site: site:transformer-circuits.pub
Search title: Circuit Tracing: Revealing Computational Graphs in Language Models
See how to search.