When a tool claims "formally verified," ask: what was proved, what's still allowed?
krishnan · x · 2026-11-10
Part 6 of krishnan's thread closes with a practical checklist: when a tool claims "formally verified," ask two questions —
- Which behavior was proved?
- Which plausible failures are still allowed?
The agent's code is held to the spec, so the spec is the real target — review it like one.
More from coding & agent
- 20 Python MCP Tools Worth Knowing, From Server Building to Gateways, Security and Eval — MaryamMiradi · 2026-11-10
- Prompting tip: describe the problem, not your solution, for better agent grilling — mattpocockuk · 2026-11-10
- The One-Person Million-Dollar AI Agency: An Agent-Stack Blueprint With the Math — boringmarketer · 2026-11-10
- Developer natively manages 25-30 parallel agent sessions on macOS with Rex — jonathan_wilke · 2026-11-10
- Pi Dash orchestrates 10 Muse Code agents with Muse Ember, rewriting 178K lines in a day — AIatMeta · 2026-11-10
- 125 prompt injections, zero executed: testing a propose-and-policy agent architecture — RI4D · 2026-11-10