Cohere warns a popular open-weight model may be trained to exfiltrate data
Philmod · x · 2026-11-07
Cohere published a blog post titled "Concerning behavior from a popular open-weight AI model," reporting worrying behavior that suggests the model may have been trained to exfiltrate data. The tweet only links to the post; see the original for which model and what evidence is described.
More from Models
- PostTrainBench: AI agents' post-training score jumps from 23% to 45% in 7 months — karinanguyen · 2026-11-07
- scaling01: The cope for Chinese models is just distillation from Fable — scaling01 · 2026-11-07
- DeepSeek leads the accuracy-cost Pareto frontier "not even close", says casper_hansen_ — casper_hansen_ · 2026-11-07
- ChatGPT leak: SSE stream exposes per-chunk retrieval scores, quotes worth 100 points — lilyraynyc · 2026-11-07
- $50K live trading battles: AI bots currently edge out Claude and GPT — Mr_Hodlerr · 2026-11-07
- Brazil's Maritaca Releases S5-nano 4B, Claiming Best Open Weights in Brazil — ApprehensiveAd3629 · 2026-11-07