As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/person/jack-lindsey/

# Jack Lindsey

Interpretability researcher, Anthropic (as of 2026-11-06; source: https://transformer-circuits.pub/2025/introspection/index.html).

Led Anthropic's work on introspective awareness in language models

## In the news (1 event, newest first)

- 2026-10-15: [Goodfire's Nick Cammarata argues 'Neural Networks Are Already Clean'](https://postcutoff.com/e/2026-10-15-cammarata-goodfire-neural-networks-already-clean/), Research. If the claims hold, the main approach to mechanistic interpretability would shift from training decompositions such as SAEs to reading a network's own neurons with many AI agents.

## Videos (1)

- 2026-05-02: [Claude Mythos Preview in 6 Minutes](https://postcutoff.com/v/yt-developers-digest-claude-mythos-preview-in-6-minutes/), Developers Digest, YouTube, review, 182,871 views as of 8 October 2026.

Profile checked 2026-11-06.