iCreatAI News
Back to main site
Skip to content
Trending storyPast story

Unfix releases an AI code fix verification tool

1 reports1 sources3 days agoUpdated

Understand this story

AI overview

Unfix has released a standalone verifier for C, C++, and firmware bug fixes. It does not generate code; instead, it reproduces the bug, applies the patch, then reverts the patch to confirm the failure reappears, and finally gives a deterministic verdict of VERIFIED, REJECTED, or NOT VERIFIABLE. Unfix says that in its demo, 6 of 10 AI patches were rejected. The tool runs entirely locally, relies on neither the cloud nor large models, and is aimed at closed networks; after one-time configuration, builds and tests can be completed offline. Currently, PR checks run only in its demo repository, and partner integrations are still being prepared; firmware verification has been run on an STM32 NUCLEO development board via ST-Link.

AI overview based on source reports · Updated 3 days ago

Latest developmentNov 11 21:14
Unfix releases a C/C++ fix verifier: 6 of 10 AI patches rejected

Coverage timeline

Follow the coverage to explore different perspectives.

Nov 11
  1. Hacker News AI
    Show HN: I checked 10 AI-written patches to real C++ projects – 6 didn't hold up

    Unfix is an independent verifier for C/C++ and firmware bug fixes that reproduces the bug on the base version, applies the fix with sanitizers on, checks other tests still pass, then reverts the fix to confirm the bug returns, returning VERIFIED, REJECTED or NOT VERIFIABLE without an LLM in the verdict. In a public benchmark of 10 AI-generated patches (from Codex CLI) against real bugs in fmt, spdlog, zlib-ng and cpp-peglib, judged against maintainers' hidden reference tests, Unfix verified 4 and rejected 6. It runs as an MCP tool in agents like Claude Code and Codex, as a GitHub PR check (demo repository only), in the terminal, and on STM32 NUCLEO boards via ST-Link.

Activity for this story

Current comparable activity
3
Peak comparable activity
10Nov 11 22:00
Change in the past 24 hours
-50%

Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.