News for hackers. Stuff that matters.

A comment on Claude Code is unusable for complex engineering tasks with the Feb updates. Parent comment

Re:Claude Code is unusable for complex engineering tasks wit... by rafaelmn on Monday April 06, 2026 @03:14PM (#47665493)
Ticket is AI generated but from what I've seen these guys have a harness to capture/analyze CC performance, so effort was made on the user side for sure.
[ Parent | on HN ]
Re:Claude Code is unusable for complex engineering tasks wit... by notatallshaw on Monday April 06, 2026 @04:02PM (#47666228)
The note at the end of the post indicates the user asked Claude to review their own chat logs. It's impossible to tell if Claude used or built a a performance hardness or just wrote those numbers based on vibes.
[ Parent | on HN ]
Re:Claude Code is unusable for complex engineering tasks wit... by dreadnip on Tuesday April 07, 2026 @02:43AM (#47671520)
The whole issue is very obviously LLM generated nonsense. The stats are way too specific and reinforce the user’ bias in typical hallucinated fashion.
[ Parent | on HN ]
Re:Claude Code is unusable for complex engineering tasks wit... by gardnr on Monday April 06, 2026 @04:38PM (#47666707)
There is this 3rd party tracker: https://marginlab.ai/trackers/claude-code/
[ Parent | on HN ]