Omar Espejel
Notes and essays on proof systems, verifiable AI, and research in progress.
I write about proof systems, verifiable AI, and research I am trying to make clear.
Essays
- 2026-04-30
Why Transformers Fit STARKs
Transformer decode is a repeated state transition over carried context. That shape maps naturally to STARK-style traces.
- 2026-04-30
Where Transformer Proof Pressure Appears
Dense arithmetic is not the whole zkML story. The interesting pressure appears in repeated softmax, normalization, range, and table-like work.
- 2026-04-30
Proof Validity Is Not Statement Validity
For verifiable AI, a valid proof is not enough. The proof surface also has to bind the model, input, output, policy, verifier domain, and artifact.
- 2026-04-21
Why Documentation Structure Fits Agent Workloads
A visual essay on how curated manifests, canonical metadata, crawler boundaries, and simple health checks make documentation easier for AI agents to retrieve and cite.