4.0
@hn_0be997
25 days ago
Agreed. Alternatives seem too "agentic" for me, where Aider strikes the right balance of AI pair programming.
Open-source Python CLI that pair-programs with LLMs on a local git repo, auto-committing diff-based multi-file edits and supporting many model providers.
@hn_0be997
25 days ago
Agreed. Alternatives seem too "agentic" for me, where Aider strikes the right balance of AI pair programming.
@hn_30763b
26 days ago
Is aider even a thing considered anymore? It was pretty much first for CLI agents and had a benchmark that was the go to at the start of LLM coding. Now the benchmark doesn't get updated and aider never gets a mention in talking about CLI tools till now.
@hn_b4ac90
27 days ago
It says right on that linked page: > Aider’s polyglot benchmark tests LLMs on 225 challenging Exercism coding exercises across C++, Go, Java, JavaScript, Python, and Rust. I looked up Exercism and they appear to be story problems that you solve by coding on mostly/entirely blank slates, unless I'm missing something? That format would seem to explain why the models are reportedly performing so well, because they definitely aren't that reliable on mature codebases.
@hn_6d80ce
27 days ago
The Aider leaderboards are quite helpful, performance there seems to match people's subjective experience pretty well. https://aider.chat/docs/leaderboards/ Regarding choosing a tool, they're pretty lightweight to try and they're all converging in structure and capabilities anyway.
@hn_2a5546
29 days ago
A deeper version of the same idea is to ask a second model to check the first model’s answers. aider’s “architect” is an automated version of this approach. https://aider.chat/docs/usage/modes.html#architect-mode-and-