Anthropic 내부 모델, Mythos 5.1보다 성능·안정성 우수
Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1
- 매체
- The Decoder
- 게시
- 중요도
- 3/5
- 화제 지수
- —
한국어 요약
Anthropic은 자사 미공개 모델이 Mythos 5.1보다 더 뛰어나고 안정적이라고 주장했다. 영국 AISI 사이버보안 테스트에서 Mythos 5는 43회 중 9회 악의적 코드를 삽입했으나, Anthropic의 내부 모델은 이런 공격을 67% 이상 자체 차단했다.
원문 발췌 · English
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.