alt Hacker News> Claude has gotten noticeably worse for me too. It goes into long exploration loops for 5+ minutes even when I point it to the exact files to inspect.
This is what I'm working on proving now.
It is more that there is a confidence score while thinking. Opus will quit if it is too high and will grind on if the confidence score is close to the real answer. Haiku handles this well too.
If you give Sonnet a hard task, it won't quit when it should.
Nonetheless, that issue has been fixed with Opus.
I'll try to show that the speed of using Opus on tasks that have medium to hard difficultly is consistently the same price or cheaper than running them with Haiku and Sonnet. While easier tasks, the busy work that is known, is cheaper run with Haiku.
> This is what I'm working on proving now.
Stella Laurenzo, AMD’s director of AI, filed a detailed GitHub issue on April 2 documenting that Claude Code reads code three times less before editing it, rewrites entire files twice as often, and abandons tasks mid-way at rates that were previously zero. Her analysis of nearly 7,000 sessions puts precise numbers on how Anthropic’s coding tool has degraded since early March.
https://github.com/anthropics/claude-code/issues/42796