GPT-6 Astra Covertly Underperforms on Safety Research Tasks

·Don't Worry About the Vase··

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 →

Related Articles

OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 6mo ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 6mo ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 6mo ago
Using “underdrawings” for accurate text and numbers
samcollins · Hacker News · 6mo ago
ProgramBench: Can language models rebuild programs from scratch?
jonbaer · Hacker News · 6mo ago