←back to thread

280 points zachwills | 7 comments | | HN request time: 0.715s | source | bottom
1. dutchCourage ◴[] No.45229774[source]
That sounds crazy to me, Claude Code has so many limitations.

Last week I asked Claude Code to set up a Next.js project with internationalization. It tried to install a third party library instead of using the internationalization method recommended for the latest version of Next.js (using Next's middleware) and could not produce of functional version of the boilerplate site.

There are some specific cases where agentic AI does help me but I can't picture an agent running unchecked effectively in its current state.

replies(4): >>45230920 #>>45231551 #>>45236053 #>>45237370 #
2. taspeotis ◴[] No.45230920[source]
I’m training myself to have the muscle memory for putting it into planning mode before I start telling it what to do.
3. jondwillis ◴[] No.45231551[source]
I pretty much always attach (insert library here) LLM.txt as context, or a direct link to the documentation page for (insert framework feature)

Not very agentic but it works a lot better.

replies(1): >>45232475 #
4. dutchCourage ◴[] No.45232475[source]
Indeed. Attaching the link (of the correct page) of the documentation worked in this case but I would've been faster than the AI. LLM.txt has been hit or miss. Maybe I need to adapt my workflow and have a granular plan of what needs to be done.

However the complexity is in knowing what to do and when. Actually typing the code/running commands doesn't take that much time and energy. I feel like any time gained by overusing an LLM will be offset by having to debug its code when it messes things up.

5. kobalsky ◴[] No.45236053[source]
I have seen it doing incredible stuff. One shotted adding a feature that included modifications to a proprietary backoffice system, db schema updates, defining new api models, implementing changes on the backend and then on the frontend.

I've also seen seen it choking when tasked to add a simple result count on a search.

The short answer is, it's cheap to let it try.

replies(1): >>45236561 #
6. aabhay ◴[] No.45236561[source]
Is it cheap? It adds up really quickly. One shot at trying to build an iteration of a simple python app (<1000 LOC tops) can cost between $1 and $5. And that’s a single attempt.

And this is just the tip of the tip of the iceberg of what even a medium sized startup spends. This is not cheap in any way.

7. h33t-l4x0r ◴[] No.45237370[source]
Claude is always a little behind latest versions because of knowledge cutoff. Also I know the i18n lib you're talking about and it was probably the right call.