←back to thread

432 points tosh | 1 comments | | HN request time: 0s | source
Show context
danenania ◴[] No.39996120[source]
People interested in Aider (which is an awesome tool) might also be interested in checking out my project Plandex[1]. It's terminal-based like Aider and has a somewhat comparable set of features, but is more focused on using LLMs to work on larger and more complex tasks that span many files and model responses. It also uses a git-style CLI approach with independent commands for each action vs. Aider's interactive shell.

I studied Aider's code and prompts quite a bit in the early stages of building Plandex. I'm grateful to Paul for building it and making it open source.

1 - https://github.com/plandex-ai/plandex

replies(8): >>39996346 #>>39996360 #>>39996792 #>>39997471 #>>39997512 #>>40002284 #>>40004973 #>>40071618 #
carom ◴[] No.39996360[source]
How do you situate changes in a file? That seems like the hard part to me since the LLM can't necessary count to output a patch with line numbers.
replies(2): >>39996418 #>>39996713 #
1. danenania ◴[] No.39996418[source]
It does use line numbers, which definitely aren't infallible. That's why a `plandex changes` TUI is included to review changes before applying. Unfortunately no one has figured out a file update strategy yet that doesn't make occasional mistakes--probably we'll need either next-gen models or fine-tuning to get there.

That said, counting isn't necessarily required to use line numbers. If line numbers are included in the file when it's sent to the model, it becomes a text analysis task rather than a counting task. Here are the relevant prompts: https://github.com/plandex-ai/plandex/blob/main/app/server/m...