Show HN: Nomos – A Go harness that stops coding agents from cheating on tests
Hi HN, Mark here. If you've pointed Claude Code, Cursor, or OpenCode at a codebase you care about and walked away thinking AI coding tools are a net negative, I pretty much agree with you. Left directly on a working branch, models optimize for shutting the compiler up on the current turn. Hit a tricky failure and they delete the failing assertion, return a hardcoded nil/true stub, rewrite the spec to match broken code, dump a 300-line function into the wrong package, or burn $15 of tokens editin
Read original source
Source record
Recorded metrics
points · 3 votes
2026-11-03 05:45:19.770Z
cumulative since publication
Research analysis
Project record
Repository: mgantlett/nomos. Source account: Hi HN, Mark here. If you've pointed Claude Code, Cursor, or OpenCode at a codebase you care about and walked away thinking AI coding tools are a net negative, I pretty much agree with you. Left directly on a working branch, models optimize for shutting the compiler up on the current turn. Hit a tricky failure and they delete the failing assertion, return a hardcoded nil/true stub, rewrite the spec to match broken code, dump a 300-line function into the wrong package, or burn $15 of tokens editin
Observed adoption & comparisons
Source votes: 3 votes (Nov 3, 2026 UTC; cumulative since publication); previous same-scope observation: 3 (Nov 2, 2026 UTC). These observations do not establish demand growth. Recent records to compare: “Show HN: R/place for Git – Open-source Git server sustaining 567 pushes/s” (Show HN, Nov 6, 2026); “Show HN: Current – Change control for AI agents (Elixir)” (Show HN, Nov 6, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Adoption decision
Evaluate it against the tool or manual workflow it would replace. The stored record supports discovery; it does not yet establish reliability, lower operating cost or commercial adoption.
Unverified requirements
Not verified: license permissions, required hardware, installation steps, maintenance status and a representative task with its failure cases.
Next test
Choose one real task and a current alternative. Record the commit, environment, input, output, elapsed time and failure behavior; retain the result before recommending adoption.