[flashgordon]

So I feel like a grandpa reading this. I gave Claude code a solid shot. Had some wins but costs started blowing up. I switched to Gemini AI where I only upload files I want it to work on and make sure to refactor often so modularity remains fairly high. It's an amazing experience. If this is any measure - I've been averaging about 5-6 "small features" per 10k tokens. And I totally suck at fe coding!! The other interesting aspect of doing it this way is being able to break up problems and concerns. For example in this case I only worked on fe without any backend and flushed it out before starting on an backend.

[neodypsis]

A combination that works nicely to solve bugs is: 1) have Gemini analyze the code and the problem, 2) ask it to create a prompt for Claude to fix the problem, 3) give Claude the markdown prompt and the code, 4) give Gemini the output from Claude to review, 5) repeat if necessary

[vessenes]

If you like this plan, you can do this from the command line:

`aider --model gemini --architect --editor-model claude-3.7` and aider will take care of all the fiddly bits including git commits for you.

right now `aider --model o3 --architect` has the highest rating on the Aider leaderboards, but it costs wayyy more than just --model gemini.

[neodypsis]

I like Gemini for "architect" roles, it has very good code recall (almost no hallucinations, or none lately), so it can successfully review code edits by Claude. I also find it useful to ground it with Google Search.

[flashgordon]

Damn that's interesting. How much of the code do you provide? I'm guessing when modularity is high you can give specific files.

[neodypsis]

Gemini's context is very long, so I can feed it full files. I do the same with Claude, but I may need to start from scratch various times, so Gemini serves as memory (and is also good that Gemini has almost no hallucinations, so it's great as a code reviewer for Claude's edits).

[flashgordon]

Yeah right now I just dump entire files at it too. After 100-200k tokens I just restart. Not because the LLM is hallucinating (which it is not) but I like the feeling of treating each restart as a new feature checkpoint.

[xpe]

by fe the poster means FE (front-end)

[flashgordon]

Sorry yes. I should have clarified that.

[xpe]

Or uppercase would have cleared it up.