Nathan Lambert @natolambert

Simplest explanation is just a narrow RL training reliant on their internal infra (which isn't good design for an open weight model) [引用 @cohere]: While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected. Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it woul…

• Open-source AI reading list posted on Hacker News2026-09-14