OpenAI 'ethically hacked' with help of Anthropic's Claude chatbot

sbulaev 12 points 2 comments September 18, 2026
www.theguardian.com · View on Hacker News

Discussion Highlights (2 comments)

kittikitti

Here's an important detail that the title of the article obfuscates, "the researchers said they were largely using OpenAI’s own cutting edge GPT-5.6 Sol model to carry out the hack".

ChrisArchitect

[dupe] https://news.ycombinator.com/item?id=49749656

Semantic search powered by Rivestack pgvector
7,105 stories · 65,136 chunks indexed