{"id":47011695,"title":"Show HN: Lucid – Catch hallucinations in AI-generated code before they ship","points":4,"user":"jordanappsite","time":1771044910,"time_ago":"12 hours ago","type":"link","content":"

Hi HN, I'm Ty. I built LUCID because I kept shipping bugs that my AI coding assistant hallucinated into existence.

Three independent papers have proven that LLM hallucination is mathematically inevitable (Xu et al. 2024, Banerjee et al. 2024, Karpowicz 2025). You can't train it away. You can't prompt it away. So I built a verification layer instead.

How it works: LUCID extracts implicit claims from AI-generated code (e.g., "this function handles null input," "this query is injection-safe," "this handles concurrent access"), then uses a second, adversarial AI pass to verify each claim against the actual implementation. You get a report showing exactly what would have shipped to production without verification.

"But can't the verifier hallucinate too?" Yes -- and that's the right question. The benchmarks below were validated by running real test suites, not by trusting LUCID's judgment. The value is that structured claim extraction + adversarial verification catches bugs that a single generation pass misses. The architecture also supports swapping LLM verification for formal methods (SMT solvers, property-based testing) per claim type as those integrations mature.

Benchmarks:

- HumanEval: 86.6% baseline -> 100% pass@5 with LUCID (164/164 problems)\n- SWE-bench: 18.3% baseline -> 30.3% with LUCID (+65.5%)\n- Both benchmarks were validated by running actual test suites, not by LLM judgment\n- LLM-as-judge actually performs worse at higher k values -- it hallucinates false positives

Three ways to use it:

1. MCP Server (Claude Code, Cursor, Windsurf) -- one config line, verification as a native tool\n2. GitHub Action -- automated verification on every PR with inline comments\n3. CLI -- npx lucid verify --repo /path/to/code

Free tier: 100 verifications/month. Get a key at https://trylucid.dev

Code: https://github.com/gtsbahamas/hallucination-reversing-system\nPaper: https://doi.org/10.5281/zenodo.18522644\nDashboard: https://trylucid.dev","url":"https://github.com/gtsbahamas/hallucination-reversing-system","domain":"github.com","comments":[],"comments_count":0}