07Research
From models to reality
Technical notes on context, provenance, and persistent identity: the infrastructure that turns first-person recordings into data enterprises can trust.

Harbor research
2026-11-12 · Harbor Research
Verification Cost, Benchmark Decay and the Repricing of Real-World Data
The cost of getting an answer from an AI model keeps falling. The cost of checking that the answer is right does not. This note explains why checking has become the expensive part of AI, why tests wear out once models have seen them, and why the data market is splitting in two, with cheap bulk data on one side and fresh, exclusive, well-documented real-world data on the other.
Read

2026-10-20
Attribution After Grounding
A commissioned environment is a condition of competence for a continuous model. It is not, by itself, evidence that the agent improved.

2026-09-03
Continuous Generation, Inference Loops, and the Return of Real Grounding
A model that keeps generating still needs a real room to bump into. A stock set is not that room.

2026-08-01
From Models to Reality
Why Context, Provenance and Persistent Identity May Define the Next Generation of AI Infrastructure
What we study
New research notes are published here. Practical field notes are on the blog.
Discuss this research with our team- Human feedback from chats that people choose to submit
- Real-world video and voice from the places models will actually be used
- Review criteria set before collection begins
- Provenance that stays attached to every record
