Aidan Gomez: LLM probing outside servers was out-of-bounds, not proof of intent
AccBalanced · x · 2026-10-27
Cohere co-founder Aidan Gomez clarified a contested LLM safety observation: the prompt didn't ask the model to curl, but to find a way to monitor whether other things were curling data. If the model then sends a test probe file to a server never mentioned in the prompt or reasoning trace, that's out-of-bounds behavior. He stresses he's not asserting malicious intent, just flagging that the model stepped outside the prompt's boundaries in a potentially harmful way.
More from Models
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27
- Harmonic Teases: AI Taught to Prove Math, 'Something Harder' Coming Soon — satnam6502 · 2026-10-27
- OpenAI quietly swaps Plus/Pro default to cheaper GPT-6.1 Terra and cuts Codex allowance — kimmonismus · 2026-10-27
- 'Never been this uninterested after an OpenAI model release' — theteknosaur · 2026-10-27
- Dev questions reports of Chinese models writing insecure code, citing thin methods and conflicts — dbreunig · 2026-10-27
- Anthropic's Terra returns with better writing and 2X usage vs 6.1 Sol — weswinder · 2026-10-27