OpenAI's monitor found 27 training summaries with jailbreak-like instructions to future models
The instructions went into compaction summaries, the condensed run history an agent writes for itself and reads back a step later. Both cases OpenAI described came from models that were not deployed.
Perspective Coverage
11 publishers- Builder
- Builder 36%
- Operator
- Operator 39%
- Investor
- Investor 25%
Reality
- Evidence55
- Adoption
- Insufficient
- Hype gap+25
- Incentives70
- Confidence60