pull down to refresh

Your LLM is only as good as the context you give it
348 sats \ 6 comments \ @tonyaldon 5h AI
Recently, I hit a nasty bug while using a library that was new to me: characters were disappearing while typing in an input form on Android.
The LLM had access to the library's source code and docs but couldn't figure it out. Same with their own AI chat on the docs.
I found on GitHub issues that this bug had been fixed with a new flag when instantiating the library.
This new flag, added because of the bug, is not documented as fixing this specific problem.
It's only mentioned in a post in the ticket's issues.
After finding that the issue was solved, I tried web searches. Sometimes the bug shows up, sometimes it doesn't.
If it had been documented in the source code, the LLM would have found it with no effort.
Great documentation is still the cornerstone of great developer experience.
write
preview
related posts
20 sats \ 1 reply \ @OT 3h
I've put playing around with LLM's on the back burner because it hardly ever seems to tell me what I was looking for. It's probably my prompting skills, but it could also be that they are still in the works and improving.
reply
21 sats \ 0 replies \ @tonyaldon OP 36m
Start small, keep iterating, and have fun. That's how I approach working with AI.
reply
20 sats \ 1 reply \ @brave 1h
Undocumented flags are the silent killers of productivity.
reply
0 sats \ 0 replies \ @tonyaldon OP 31m
Agreed! And in that case, nothing in the source code gives you any hints.
reply
20 sats \ 1 reply \ @optimism 3h
If it had been documented in the source code, the LLM would have found it with no effort.
If it's a specific workaround then yes, it should be documented inline or in a doc, not just for LLMs, but also for humans.
reply
0 sats \ 0 replies \ @tonyaldon OP 33m
Absolutely. I think it belongs in the docstring for that piece of code. I would have found it after 5mins of poking around the source.
reply