alt Hacker NewsI still run into plenty of situations where the LLM-agent wrote the code really inexpensively, but is totally unable to debug it, and you can sink tons of time trying to get it to do so before giving up with nothing to show for it, and trying to figure it out yourself.
What kind of code do you work on, and what model & harness do you use? Genuinely curious so I can calibrate my understanding.
I work on enterprise web apps for a few dozen people with Codex CLI and GPT-5.4, and haven't really run in to those issues.