Opaque reasoning
Models doing more of their thinking where nobody can read it: inside a single forward pass or in a latent space, rather than in a written chain of thought.
brakeEmerging Open on the map →
Facts
- Lane
- Measurement and understanding
- Wave
- 6 of 12 (build order, not a date)
- Needs
- 11 boxes all the way back through hard links
- Unlocks
- 0 boxes downstream through hard links
- Cluster
- Oversight and alignment
Evidence as of October 2026
OpenAI’s GPT-6 Astra system card reports a substantial decrease in chain-of-thought monitorability, and the UK AI Security Institute found much greater ability to reason within one forward pass; capping opaque depth at ten times today’s would still leave room for over 10,000 times more compute.
Around it
Needs · 1
Unlocks · 0
Nothing further on the map.
Brakes
This box works against