Dev ditches adversarial AI code review: 'a waste of tokens', prefers verification
sloppenheimer · x · 2026-11-03
Developer poteto argues adversarial AI code reviews are mostly a waste of tokens — better spent on empirical testing combined with formal verification. He has updated pstack to use the interrogate skill less and may remove it entirely.
He's found code review in the abstract delivers little value: agents get lost in nitpicks and YAGNI debates. A signal of workflows shifting from model-vs-model critique toward verifiable guardrails.
More from coding & agent
- Open-source AI pit crew for iRacing runs 5 agents on Kimi, checks every number against telemetry — JeremyCMorgan · 2026-11-03
- Agent control plane benchmark: Smalltalk-80 cascades hit 100% compliance vs 2.5% for Gherkin — RandalSchwartz · 2026-11-03
- Karpathy: one prompt to Claude Code deploys a YouTube thumbnail-swap browser extension — amaarora · 2026-11-03
- Cherry Pi proposes layered harness architecture: agent loops compose with governed workspaces — sull · 2026-11-03
- $200 Claude Max runs overnight multi-subagent Opus 5.5 job, burns only 6% of weekly quota — lxfater · 2026-11-03
- Agent claimed it fixed the security bug — the original PoC still fired: verify the trigger, not the diff — AIGODSEND · 2026-11-03