News for hackers. Stuff that matters.

A comment on AI Agents: Less Capability, More Reliability, Please. Parent comment

Re:AI Agents: Less Capability, More Reliability, Please by bongodongobob on Monday March 31, 2025 @01:28PM (#43537500)
I think this is one of the core issues people have when trying to program with them. If you have a long conversation with a bunch of edits, it will start to get unreliable. I frequently start new chats to get around this and it seems to work well for me.
[ Parent | on HN ]
Re:AI Agents: Less Capability, More Reliability, Please by _bin_ on Monday March 31, 2025 @07:15PM (#43541024)
Yes, this definitely helps. It's just incredibly annoying because you have to dump context back into it, re-type stuff, consolidate stuff from the prior conversation, etc.
[ Parent | on HN ]
Re:AI Agents: Less Capability, More Reliability, Please by dr_kiszonka on Monday March 31, 2025 @11:08PM (#43542417)
Have the AI maintain a document (a local file or in canvas) with project goals, structure, setup instructions, current state, change log, todos, caveats, etc. You might need to remind it to keep it up-to-date, but I find this approach quite useful.
[ Parent | on HN ]