←back to thread

549 points thecr0w | 1 comments | | HN request time: 0.217s | source
Show context
throwaway314155 ◴[] No.46183616[source]
Somehow I suspect Claude Code (in an interactive session with trial, error, probing, critiquing, perusing, and all the other benefits you get) would do better. This example seems to assume Claude can do things in "one shot" (even the later attempts all seem to conceal information like it's a homework assignment).

That's not how to successfully use LLM's for coding in my experience. It is however perhaps a good demonstration of Claude's poor spatial reasoning skills. Another good demonstration of this is the twitch.tv/ClaudePlaysPokemon where Claude has been failing to beat pokemon for months now.

replies(2): >>46183643 #>>46183665 #
CharlesW ◴[] No.46183665[source]
Using https://github.com/anthropics/claude-code/tree/main/plugins/... with style-supporting instructions and context would've improved the outcome as well.
replies(2): >>46183669 #>>46184029 #
1. aidos ◴[] No.46184029[source]
Is the skill effectively just adding a little extra context here though? Doesn’t strike me as the sort of context that would improve the outcome.

https://github.com/anthropics/claude-code/blob/main/plugins/...