Below the Harness: Governing a Multi-Model, Multi-Harness World
First reported · 52d ago · 1 source
Crest summary — written by AI from the 1 source below; every figure is checked against them · model deepseek-chat
Summary
Docker published a blog post arguing that AI systems need a new trust model for a multi-model, multi-harness world, citing Norm Hardy's 1988 confused deputy problem.
Key facts
- Docker published the post on 2026-09-02.
- The post references Norm Hardy's 1988 description of the confused deputy problem.
- Docker states the future is a multi-model, multi-harness world.
Why it matters
Builders and buyers of AI tooling are told existing trust assumptions may not hold when models and harnesses are combined, so permission handling deserves scrutiny.
Companies
Original sources (1)
The report this event was built from. Crest of Tech keeps no article bodies: the full text is at each source.
- DockerOfficial · PrimaryBelow the Harness: Governing a Multi-Model, Multi-Harness World · By Srini SekaranRead at Docker