HN Explorer

What's the worst bug an AI coding agent silently introduced into your code?

2 points by riyashikanedunc ↗ HN
I'm researching AI code reliability — specifically bugs that pass existing tests but cause real failures. Interested in patterns: what breaks, how it's caught, and how long it takes to debug. Happy to share aggregated findings with everyone who responds.

7 comments

[ 3.6 ms ] story [ 28.6 ms ] thread
addaon
Way too early to say. The bugs being silently introduced now will take lives down the road.
[dead] jtyas
[flagged]
Benjaminsen
Not a bug as such, but Claude _really_ likes Claudeflare solutions to things that are trivially solved with my own server.

Until I structurally started enforcing defaulting to use my own hardware it was always off on a sidetrack to use some Cloudflare service to solve trivial problems.

bergie
On a piece of navigation software, GLM hallucinated astro tables instead of using a library. I wondered why my sun sight was 1000NM off, and then it confessed.

On the current offshore passage I got to within 7NM of GNSS position, so the fixed version works. 7NM might sound a lot, but from the deck of a small boat in big seas it isn't bad, and totally enough for making landfall.