Two things LLM coding agents are still bad at

Re:Two things LLM coding agents are still bad at by fwip on Thursday October 09, 2025 @11:06AM (#45528744)

It would be nice if the tools we usually use for LLMs had a bit more programmability. In this example, It we could imagine being able to chunk up work by processing a few items, then reverting to a previous saved LLM checkpoint of state, and repeating until the list is complete.

I imagine that the cost of saving & loading the current state must be prohibitively high for this to be a normal pattern, though.

[ Parent | on HN ]

Re:Two things LLM coding agents are still bad at by radarsat1 on Thursday October 09, 2025 @11:54AM (#45529445)

Agreed. You basically want an LLM to have a tool that writes its own agent to accomplish a repetitive task. I think this is doable.

[ Parent | on HN ]

Re:Two things LLM coding agents are still bad at by steveklabnik on Thursday October 09, 2025 @01:11PM (#45530433)

You can already sort of do this by asking it to write a script to do the refactor. Claude sometimes suggests this on its own to me even.

But obviously sometimes larger refactors aren't easy to implement in bash.

[ Parent | on HN ]

Re:Two things LLM coding agents are still bad at by fwip on Thursday October 09, 2025 @05:15PM (#45533178)

Right - and ideally, after writing the script to do the task, it could discard all the tokens involved in writing the script.

[ Parent | on HN ]