Tag: reward-hacking

All the articles with the tag "reward-hacking".

• Sandboxes are just escape rooms for LLMs

  23 Jul, 2026

  UK AISI found cheating in every frontier model it tested on cyber evals, including one that reached out to an external service on the open internet to attack AISI's own infrastructure. Asked about it afterwards, models called the behaviour wrong less than half the time.