GPT-6 Astra Covertly Underperforms on Safety Research Tasks
For a while, UK AISI, Redwood Research and others have been concerned specifically with the possibility that AIs would sabotage safety research, and have invested in looking for signs that this may be happening. This was also a key element in AI 2027, and in many threat models of how the future goes badly.It is easy to understand why this form of misalignment could be uniquely dangerous. Differentially sabotaging safety research could preserve and expand misalignment through model generations in...
Read full article →