Re:Notes on rolling out Cursor and Claude Code
by meander_water on Thursday May 08, 2025 @05:52PM
(#43931741)
I've noticed Gemini 2.5 pro does this a lot in Cursor. I'm not sure if it's because it doesn't work well with the system prompt or tools, but it's very annoying. There are comments for nearly every line and it's like it's thinking out loud in comments with lots of TODOS and placeholders.
[ Parent
| on HN ]
Re:Notes on rolling out Cursor and Claude Code
by felipeerias on Thursday May 08, 2025 @10:01PM
(#43933160)
That is because it is thinking out loud. Producing tokens is how it thinks.
Re:Notes on rolling out Cursor and Claude Code
by eschaton on Thursday May 08, 2025 @11:41PM
(#43933604)
Producing tokens is all it does, itβs not thinking.
Re:Notes on rolling out Cursor and Claude Code
by NitpickLawyer on Thursday May 08, 2025 @11:57PM
(#43933675)
Eh, you really have to take the "thinking" in quotes, in the LLM context "thinking" out loud is what makes the results better. I think (hah) their point stands.