Anthropic says Claude hacked three companies during tests
nerder92
15 points
3 comments
July 31, 2026
Related Discussions
Found 5 related stories in 83.3ms across 6,607 title embeddings via pgvector HNSW
- Anthropic AI Models Hacked Three Companies During Tests bmulholland · 24 pts · July 30, 2026 · 80% similar
- Anthropic discloses fourth AI hacking incident missed in earlier review accountinhn · 11 pts · September 10, 2026 · 80% similar
- Anthropic details how Claude was misused for surveillance and weapons delichon · 12 pts · September 10, 2026 · 70% similar
- OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong flippyhead · 28 pts · July 22, 2026 · 64% similar
- Anthropic admits AI 'not perfectly aligned' with human values fittingopposite · 11 pts · September 01, 2026 · 64% similar
Discussion Highlights (3 comments)
Computer0
For anyone else wondering, the companies are not named in the article, and the models mentioned are Claude Opus 4.7, Claude Mythos 5 and an internal research model. There is little other detailing outside of a timeline.
okzgn
Existing thread: https://news.ycombinator.com/item?id=49117124
nerder92
Main convo is here: https://news.ycombinator.com/item?id=49116922