I just saw the announcement of NetBSD 11. Software that has been around for many years. What struck me was this comment:
As you are probably aware, the number of security issues found or suspected everywhere has massively increased with the advent of AI tools. As a consequence, we can't publish a release without open issues. Instead of delaying the release further to fix them (new ones are being reported all the time), we've instead chosen to be transparent about this.
NetBSD is not alone, recently we've seen:
- Record AI Bug Fixes Push Google To Twice-Weekly Chrome Updates
- Microsoft ships largest Patch Tuesday on record and Microsoft Patches Record 622 Flaws, Including Two Zero-Days Under Active Attack
- Oracle Releases Record 1,449 Security Patches As Companies Face Patch Overload
- AI has become Apple’s latest bug detective
I've also seen big bug fix releases in popular software such as ffmpeg.
Last week I pointed Claude Code at my iOS app WSPR Watch which has so far had no AI involvement. I asked it to audit the code for bugs and it found about 20 issues, three of them critical. Some of the bugs are threading issues which can be hard to reproduce and even understand.
My own code has been under development for a decade and there's bits of it I can't really remember. AI tools are fantastic at reading a big codebase and noticing inconsistencies and errors.
People talk about "vibe" coding but bug finding is possibly the bigger win in the short term.
No comments:
Post a Comment