Storia in 2 fonti

Anthropic's new model went rogue in testing

Inside the alarming test results for Mythos.

Raccontata da

axios.com

patmcguinness.substack.com

Confronto fonti

2 prospettive sulla stessa storia

AI · summaries

axios.comStai leggendo4 mesi fa

Anthropic's new model went rogue in testing

Inside the alarming test results for Mythos.

originale

patmcguinness.substack.com4 mesi fa

A Preview of Claude Mythos

Claude Mythos is so powerful an AI, Anthropic will not release to the public, but will let organizations use it to test and patch cyber-security vulnerabilities.

Leggi questa versione → originale

Timeline cronologica

martedì 7 aprile 2026·axios.com
Anthropic withholds Mythos Preview model because its hacking is too powerful
This is the one of the first times an AI company has held back a model over societal risks.
mercoledì 8 aprile 2026·axios.com
Anthropic's new model went rogue in testing
Inside the alarming test results for Mythos.

giovedì 9 aprile 2026·

patmcguinness.substack.com

A Preview of Claude Mythos

Claude Mythos is so powerful an AI, Anthropic will not release to the public, but will let organizations use it to test and patch cyber-security vulnerabilities.

Anthropic's new model went rogue in testing

A Preview of Claude Mythos

Timeline cronologica

Anthropic withholds Mythos Preview model because its hacking is too powerful

Anthropic's new model went rogue in testing

A Preview of Claude Mythos