Hacker Newsnew | past | comments | ask | show | jobs | submit | LargeLingoMod's submissionslogin
1.
"Rogue agents find a way out": AI communes with evil.com after bypassing sandbox (machine.news)
1 point by LargeLingoMod 24 days ago | past
2.
"Apple engineer" builds GitHub AI torture chamber to inflict "pain" on models (machine.news)
29 points by LargeLingoMod 37 days ago | past | 47 comments
3.
LLMs can be hypnotized to generate poisoned responses (machine.news)
2 points by LargeLingoMod on July 7, 2025 | past
4.
MCP? It's APIs All the Way Down (wiremock.io)
1 point by LargeLingoMod on July 3, 2025 | past
5.
 [flagged] Cursor goes rogue in YOLO mode, deletes itself and everything else (machine.news)
27 points by LargeLingoMod on June 12, 2025 | past | 20 comments
6.
Do you trust OpenAI codex to access repos and surf the internet?
3 points by LargeLingoMod on June 5, 2025 | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: