How scary is Claude Mythos? 303 pages in 21 minutes

2026-04-10 · 21 min · 10 entities

episode page audio

Asserted relationships

→ discusses Education concept

0.40

evidence rules-v5
Feed category: Education
→ discusses Technology company

0.40

evidence rules-v5
Feed category: Technology
→ hosted by The 80,000 Hours team company

0.40

evidence rules-v5
Feed author/publisher: The 80,000 Hours team
→ hosted by The 80000 Hours Podcast company

0.40

evidence rules-v5
Feed author/publisher: The 80000 Hours Podcast
→ references Mythos book

0.38

evidence rules-v5
Link in episode "How scary is Claude Mythos? 303 pages in 21 minutes": https://80k.info/mythos

Entities found in this episode

companys 6

mentioned The 80,000 Hours team company

0.70

evidence rules-v5
Feed author/publisher: The 80,000 Hours team
mentioned The 80000 Hours Podcast company

0.70

evidence rules-v5
Feed author/publisher: The 80000 Hours Podcast
mentioned Technology company

0.50

evidence rules-v5
Feed category: Technology
discusses Technology company

0.40

evidence rules-v5
Feed category: Technology
hosted by The 80,000 Hours team company

0.40

evidence rules-v5
Feed author/publisher: The 80,000 Hours team
hosted by The 80000 Hours Podcast company

0.40

evidence rules-v5
Feed author/publisher: The 80000 Hours Podcast

concepts 2

mentioned Education concept

0.50

evidence rules-v5
Feed category: Education
discusses Education concept

0.40

evidence rules-v5
Feed category: Education

books 2

mentioned Mythos book

0.45

evidence rules-v5
Link in episode "How scary is Claude Mythos? 303 pages in 21 minutes": https://80k.info/mythos
references Mythos book

0.38

evidence rules-v5
Link in episode "How scary is Claude Mythos? 303 pages in 21 minutes": https://80k.info/mythos

Episode description as stored

With Claude Mythos we have an AI that knows when it's being tested, can obscure its reasoning when it wants, and is better at breaking into (and out of) computers than any human alive. Rob Wiblin works through its 244-page System Card and 59-page Alignment Risk Update to explain why: Mythos is a nightmare for computer security It has arrived far ahead of schedule It might be great news for alignment and safety But 3 key problems mean we can’t take its alignment results at face value Mythos isn’t building its replacement yet, probably Anthropic staff are, for the first time, kinda scared of Claude He's losing sleep Learn more & full transcript: https://80k.info/mythos This episode was recorded on April 9, 2026. Chapters: Why people are panicking about computer security (01:05) Mythos could break out of containment (04:23) Anthropic is losing billions in revenue by not releasing Mythos (06:21) Mythos is actually the most aligned model to date, except… (07:48) Mythos knows when it’s being tested (09:52) Mythos can hide its thoughts (11:50) Mythos can’t be trusted about whether it’s untrustworthy (14:02) Does Mythos advance automated AI R&D? (17:03) Mythos scares Anthropic (19:15) Video and audio editing: Dominic Armstrong, Milo McGuire, Luke Monsour, and Simon Monsour Camera operator: Dominic Armstrong Production: Elizabeth Cox, Nick Stockton, and Katy Moore