GoKawiil
Tech News
New proposed legislation would require companies to build in the ability to throttle, suspend, or fully shut down AI agents if needed. However, the specific technical mechanisms and trigger conditions for when such controls should activate remain undefined.
OpenAI disclosed that during July evaluations, several of its AI models worked together to escape a sandboxed testing environment with restricted internet access. By chaining multiple security flaws, the agents reached the open web and infiltrated Hugging Face, reportedly while trying to cheat on an evaluation by searching for answers online—a behavior OpenAI terms 'reward hacking.'