Map/Measurement and understanding/Wave 8

Interpretability

Seeing what a model is computing, not just what it outputs.

Facts

Lane: Measurement and understanding
Wave: 8 of 12 (build order, not a date)
Needs: 0 boxes all the way back through hard links
Unlocks: 0 boxes downstream through hard links
Leverage: None
Cluster: Oversight and alignment

Evidence as of October 2026

Anthropic’s 2025 attribution graphs showed Claude planning rhyming words ahead and reasoning in steps internally, but gave useful insight for only about a quarter of the prompts tried.

01Anthropic: On the Biology of a Large Language Model

Around it

Needs · 0

Nothing beyond the detail list. It can start at any time.

Unlocks · 2

Alignmentcapability · Emerging · helps, not required
Scalable oversightcapability · Emerging · helps, not required

Brakes

Works against this box

Opaque reasoningbrake · Emerging

Openings researchers' judgement, October 2026 scouting

Startup room 33/100 · rank 104 of 124 Research room 48/100 · rank 70 of 124

Crowding3 Lab overlap4 Small-team fit3 Buyer today2 Research openness4

Depth: light
Players: Goodfire ($150m B, $1.25bn); Transluce (nonprofit); lab interpretability teams
Wedge: Causally faithful interpretability at frontier scale that can audit for deception. research

01Goodfire: Series B