Episode

"Even “illegible” Mythos reasoning traces seem pretty legible" by faul_sname

Podcast
LessWrong (Curated & Popular)
Published
Jun 11, 2026
Duration seconds
462
Processing state
not_requested
Canonical source
https://www.buzzsprout.com/2037297/episodes/19329842-even-illegible-mythos-reasoning-traces-seem-pretty-legible-by-faul_sname.mp3
Audio
https://www.buzzsprout.com/2037297/episodes/19329842-even-illegible-mythos-reasoning-traces-seem-pretty-legible-by-faul_sname.mp3
JSON
/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/even-illegible-mythos-reasoning-traces-seem-pretty-legible-by-faul-sname
Markdown
/podcast/lesswrong-curated-popular-5643401/even-illegible-mythos-reasoning-traces-seem-pretty-legible-by-faul-sname.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/even-illegible-mythos-reasoning-traces-seem-pretty-legible-by-faul-sname/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/even-illegible-mythos-reasoning-traces-seem-pretty-legible-by-faul-sname.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

The Claude Fable 5/Mythos 5 System Card has a section in which they talk about illegible reasoning, and provide an "extreme" example thereof. Models developing their own uninterpretable, unmonitorable internal language has been a major theoretical concern for a while, and when o3 was released last year with its disclaim overshadow disclaim vantage style word salad CoT, it seemed like the problem had become real and immediate. And yet, since o3, other model families have not appeared to hav...