←back to thread

Claude Code Checkpoints

(claude-checkpoints.com)
184 points punnerud | 4 comments | 28 Aug 25 09:16 UTC | HN request time: 0.001s | source
Show context
endymion-light ◴[28 Aug 25 12:53 UTC] No.45051586[source]▶
i love the process of AI vibe coding slowly re-inventing the normal structures of software development

how long until we start seeing software products for scrum management and t-shirt size estimation for claude code

introduce waterfall methodology to the LLM!

replies(3): >>45051609 #>>45051780 #>>45054478 #
CuriouslyC ◴[28 Aug 25 13:15 UTC] No.45051780[source]▶
T shirt estimation doesn't make any sense for AI dev, not one bit. They get epic long features done in hours, and all the shirt sizing comes from cases where the agent circles the drain and needs to be guided, which isn't predictable.

The shirt sizes now are for manual acceptance testing.

replies(2): >>45051834 #>>45052266 #
1. endymion-light ◴[28 Aug 25 13:20 UTC] No.45051834[source]▶
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

replies(1): >>45051998 #
2. CuriouslyC ◴[28 Aug 25 13:36 UTC] No.45051998[source]▶
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.
replies(2): >>45052072 #>>45053750 #
3. endymion-light ◴[28 Aug 25 13:41 UTC] No.45052072[source]▶
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!
4. thelittleone ◴[28 Aug 25 15:54 UTC] No.45053750[source]▶
I found a boost adding LikeC4 to the spec.