All Topics
All Topics
Technology
Technology
AI
AI
Business
Business
Entertainment
Entertainment
News
News
Programming
Programming
Security
Security
Science
Science
Design
Design
Environment
Environment
Finance
Finance
Crypto
Crypto
Politics
Politics
Sports
Sports
Education
Education
Gaming
Gaming
Art
Art
Music
Music
Health
Health
Books
Books
Food
Food
Travel
Travel
Personal
Personal
Bluesky
Twitter

Reflections on debugging with AI coding agents

By

gm678

2h ago· 105 min readenOpinion

Summary

The author reflects on their experience using AI coding agents since late last year, noting the ironic dynamic where AI agents make mistakes that would be unacceptable from a human employee, yet the author's response is to scale up and deploy more agents. They recount a specific instance where they used GPT (around version 5.0 or 5.1) to help debug a UI interaction bug in code that lacked tests and couldn't use git bisect, asking Codex to bisect between date ranges to find the bug's origin.

Source

Hacker NewsReflections on debugging with AI coding agentsdanluu.com

Key quotes

· 3 pulled
An agent will do something that, if a human did it, you'd immediately fire them.
My reaction, of course, is to act as if this is great and spin up a thousand agents so they can do even more of that.
I had GPT (maybe 5.0 or 5.1) try to find the source of a bug. Naturally, this code didn't have tests and git bisect wouldn't work.
Snippet from the RSS feed
I've been using AI fairly heavily since last November and the whole thing is a funny experience. An agent will do something that, if a human did it, you'd immediately fire them. My reaction, of course, is to act as if this is great and spin up a thousand

You might also wanna read

Comments

Sign in to join the conversation.

No comments yet. Be the first.