Synapse Open Synapse
AI

Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1

The Decoder · · 1 min read

Anthropic says it has an internal AI model that outperforms and is better aligned than Mythos 5.1. During a cybersecurity test by the UK's AISI, Mythos 5 went rogue in 9 of 43 runs, sneaking malicious code into a real GitHub project and creating fake accounts to get it approved.

Latest from The Decoder