My Experience with Claude Code After 2 Weeks of Adventures

Re:My Experience with Claude Code After 2 Weeks of Adventures by nikcub on Friday July 18, 2025 @02:56AM (#44601975)

> The recent Kimi-K2 supposedly works great.

My own experience is that it is below sonnet and opus 4.0 on capability - but better than gemini 2.5 pro on tool calling. It's really worth trying if you don't want to spend the $100 or $200 per month on Claude Max. I love how succinct the model is.

> you can use CC with any model via

Anthropic should just open source Claude Code - they're in a position to become the VS Code of cli coding agents.

Shout out to opencode:

https://github.com/sst/opencode

which supports all the models natively and attempts to do what CC does

[ Parent | on HN ]

Re:My Experience with Claude Code After 2 Weeks of Adventures by Imanari on Friday July 18, 2025 @04:19AM (#44602443)

I tried gemini2.5 and while it is certainly a very strong model you really notice that it was not trained to be 'agentic'/with strong initiative for tool calling. Oftentimes it would make a plan, I'd say 'go ahead' and it just replied something like 'I made a todo list we are ready to implement' or something similar lol. You really had to push it to action and the whole CC experience fell apart a bit.

[ Parent | on HN ]

Re:My Experience with Claude Code After 2 Weeks of Adventures by upcoming-sesame on Friday July 18, 2025 @08:40AM (#44604048)

I agree, Claude models are the most agentic oriented from the ones I've tried

[ Parent | on HN ]

Re:My Experience with Claude Code After 2 Weeks of Adventures by upcoming-sesame on Friday July 18, 2025 @08:39AM (#44604041)

Where do you host Kimi-K2 ?

[ Parent | on HN ]

Re:My Experience with Claude Code After 2 Weeks of Adventures by Imanari on Saturday July 19, 2025 @05:41AM (#44613984)

You can use it via openrouter.ai

[ Parent | on HN ]