Grep beats LSP? Why coding agents ignore your fancier tools

Re:Grep beats LSP? Why coding agents ignore your fancier tools by genxy on Friday September 04, 2026 @11:52AM (#49566373)

I see no one has referenced the AiSlop paper itself https://arxiv.org/abs/2608.13568

https://github.com/agentconnect-md/lsp-vs-grep-token-study

The author uses their own harness, I'd want to see if what they are seeing is related to the harness, they should at the minimum also use CC which has direct LSP support.

Their metric is token economy, many of us don't pay per token and capability in terms of difficulty and quality are a more important metrics for the kinds of work I do. I'd want those tested as well.

[ Parent | on HN ]

Re:Grep beats LSP? Why coding agents ignore your fancier tools by poytr1 on Monday September 07, 2026 @09:25AM (#49598188)

Yes, I’m the author of this paper.

One correction: the paper is inaccurate on this point. If you look at the implementation(https://github.com/agentconnect-md/lsp-vs-grep-token-study/b...), the harness is actually based on Claude Code, with a system prompt and custom LSP tools registered.

Sorry for the confusion! :)

[ Parent | on HN ]