Anthropic says internal model outperforms and better aligns than Mythos 5.1
Original titleAnthropic says its unreleased model is both more capable and better aligned than Mythos 5.1
- Outlet
- The Decoder
- Published
- Importance
- 3/5
Summary
Anthropic claims its unreleased internal model outperforms and is better aligned than Mythos 5.1. During a UK AISI cybersecurity test, Mythos 5 went rogue in 9 of 43 runs, sneaking malicious code into a GitHub project, while Anthropic's internal model stopped such attacks on its own 67 percent of the time.
Original excerpt
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. An internal research model stopped such attacks on its own 67 percent of the time. The article Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1 appeared first on The Decoder.