←back to thread

Gemini CLI

(blog.google)
1336 points sync | 2 comments | | HN request time: 0.591s | source
Show context
joelm ◴[] No.44379446[source]
Been using Claude Code (4 Opus) fairly successfully in a large Rust codebase, but sometimes frustrated by it with complex tasks. Tried Gemini CLI today (easy to get working, which was nice) and it was pretty much a failure. It did a notably worse job than Claude at having the Rust code modifications compile successfully.

However, Gemini at one point output what will probably be the highlight of my day:

"I have made a complete mess of the code. I will now revert all changes I have made to the codebase and start over."

What great self-awareness and willingness to scrap the work! :)

replies(8): >>44379714 #>>44380383 #>>44380768 #>>44380866 #>>44381146 #>>44381754 #>>44383245 #>>44386866 #
ZeroCool2u ◴[] No.44379714[source]
Personally my theory is that Gemini benefits from being able to train on Googles massive internal code base and because Rust has been very low on uptake internally at Google, especially since they have some really nice C++ tooling, Gemini is comparatively bad at Rust.
replies(5): >>44380405 #>>44380865 #>>44381697 #>>44382948 #>>44383662 #
leoh ◴[] No.44382948[source]
>Personally my theory is that Gemini benefits from being able to train on Googles massive internal code base and because Rust has been very low on uptake internally at Google, especially since they have some really nice C++ tooling, Gemini is comparatively bad at Rust.

Were they to train it on their C++ codebase, it would not be effective on account of the fact that they don't use boost or cmake or any major stuff that C++ in the wider world use. It would also suggest that the user make use of all kinds of non-available C++ libraries. So no, they are not training on their own C++ corpus nor would it be particularly useful.

replies(1): >>44385355 #
1. leoh ◴[] No.44385355[source]
Excuse me why was this downvoted so aggressively??
replies(1): >>44388969 #
2. simianwords ◴[] No.44388969[source]
How can they train on internal codebase without leaking specifics?