News for hackers. Stuff that matters.

A comment on Claude Code Checkpoints. Parent comment

Re:Claude Code Checkpoints by endymion-light on Thursday August 28, 2025 @09:20AM (#45051834)
My experience with AI tooling is that while it's really useful and great - I don't think i've ever seen a LLM complete an epic long feature well full stop.

Don't get me wrong, it's definitely improved my workflow and efficiency, but you must be winning at roulette if the model is performing well on anything that can't be googled and implemented witihn a similar amount of time.

unless it's claude, where even simple styling changes seem to become epics just when it wants to spit out an extra few thousands lines of code

[ Parent | on HN ]
Re:Claude Code Checkpoints by CuriouslyC on Thursday August 28, 2025 @09:36AM (#45051998)
If you go back and forth with chatgpt/gemini on architectural details first, then get chatgpt to produce a hyper detailed spec (like, almost a program claude can execute), you can get claude to run for 2-3 hours at a shot (particularly with a hook to prevent early stopping). Require >85% test coverage, and bake very clear e2e test paths into the spec, and Claude can come surprisingly close to one shotting big things.
[ Parent | on HN ]
Re:Claude Code Checkpoints by thelittleone on Thursday August 28, 2025 @11:54AM (#45053750)
I found a boost adding LikeC4 to the spec.
[ Parent | on HN ]
Re:Claude Code Checkpoints by endymion-light on Thursday August 28, 2025 @09:41AM (#45052072)
Fair enough! I'll need to give it a try - I tend to mostly use these agents as idea testers as have found them limiting beyond those concepts, but it sounds like they may be quite useful using this spec, thanks!
[ Parent | on HN ]