Show HN: Autofix Bot – Hybrid static analysis and AI code review agent
36 points by sanketsaurav
by yoelhacks
1 subcomments
$8/100k tokens strikes me as potentially a TON if the idea is that we're going to be running this as part of the iterative local development cycle (or god forbid letting agents run it whenever they decide). As you mentioned, one of the issues with AI generated code is often that it writes too much and needs direction on shrinking down.
I could easily see hitting 10k+ LOC on routine tickets if this is being run on each checkpoint. I have some tickets that require moving some files around, am I being charged on LOC for those files? Deleted files? Newly created test files that have 1k+ lines?
by tarun_anand
1 subcomments
Congratulations!! Anchoring is important. What about other parts of the code review like coding guidelines, perf issues etc?
by ramon156
1 subcomments
How does this compare to gemini-code-assist? Rn its one of the best imo
by _pdp_
2 subcomments
What is the difference between this and let's say Claude Code using something like semgrep as a tool?
Also I don't think this tool should be in the developer flow as in my experience it is unlikely to run it on the regular. It should be something that is done as part of the QA process before PR acceptance.
I hope this helps and good luck.
by dlahoda
1 subcomments
we use rust, sql, typescript. how statically covered these?
by nickphx
0 subcomment
"shifted bottleneck to code review"... understatement of decade.