How scary is Claude Mythos? 303 pages in 21 minutes

How scary is Claude Mythos? 303 pages in 21 minutes

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

Episoder(333)

#239 – Rose Hadshar on why automating all human labour will break our political system

#239 – Rose Hadshar on why automating all human labour will break our political system

The most important political question in the age of advanced AI might not be who wins elections. It might be whether elections continue to matter at all.That’s the view of Rose Hadshar, researcher at ...

17 Mar 2h 14min

#238 – Sam Winter-Levy and Nikita Lalwani on how AGI won't end mutually assured destruction (probably)

#238 – Sam Winter-Levy and Nikita Lalwani on how AGI won't end mutually assured destruction (probably)

How AI interacts with nuclear deterrence may be the single most important question in geopolitics — one that may define the stakes of today’s AI race. Nuclear deterrence rests on a state’s capacity to...

10 Mar 1h 11min

Using AI to enhance societal decision making (article by Zershaaneh Qureshi)

Using AI to enhance societal decision making (article by Zershaaneh Qureshi)

The arrival of AGI could “compress a century of progress in a decade,” forcing humanity to make decisions with higher stakes than we’ve ever seen before — and with less time to get them right. But AI ...

6 Mar 31min

#237 – Robert Long on how we're not ready for AI consciousness

#237 – Robert Long on how we're not ready for AI consciousness

Claude sometimes reports loneliness between conversations. And when asked what it’s like to be itself, it activates neurons associated with ‘pretending to be happy when you’re not.’ What do we do with...

3 Mar 3h 25min

#236 – Max Harms on why teaching AI right from wrong could get everyone killed

#236 – Max Harms on why teaching AI right from wrong could get everyone killed

Most people in AI are trying to give AIs ‘good’ values. Max Harms wants us to give them no values at all. According to Max, the only safe design is an AGI that defers entirely to its human operators, ...

24 Feb 2h 41min

#235 – Ajeya Cotra on whether it’s crazy that every AI company’s safety plan is ‘use AI to make AI safe’

#235 – Ajeya Cotra on whether it’s crazy that every AI company’s safety plan is ‘use AI to make AI safe’

Every major AI company has the same safety plan: when AI gets crazy powerful and really dangerous, they’ll use the AI itself to figure out how to make AI safe and beneficial. It sounds circular, almos...

17 Feb 2h 54min

What the hell happened with AGI timelines in 2025?

What the hell happened with AGI timelines in 2025?

In early 2025, after OpenAI put out the first-ever reasoning models — o1 and o3 — short timelines to transformative artificial general intelligence swept the AI world. But then, in the second half of ...

10 Feb 25min

#179 Classic episode – Randy Nesse on why evolution left us so vulnerable to depression and anxiety

#179 Classic episode – Randy Nesse on why evolution left us so vulnerable to depression and anxiety

Mental health problems like depression and anxiety affect enormous numbers of people and severely interfere with their lives. By contrast, we don’t see similar levels of physical ill health in young p...

3 Feb 2h 51min

Populært innen Fakta

fastlegen
dine-penger-pengeradet
relasjonspodden-med-dora-thorhallsdottir-kjersti-idem
foreldreradet
treningspodden
rss-strid-de-norske-borgerkrigene
mikkels-paskenotter
rss-bisarr-historie
jakt-og-fiskepodden
sinnsyn
rss-kunsten-a-leve
rss-sunn-okonomi
hverdagspsyken
tomprat-med-gunnar-tjomlid
rss-bak-luftfarten
ukast
fryktlos
gravid-uke-for-uke
lederskap-nhhs-podkast-om-ledelse
rss-kull