5 points iosifnicolae2 | 1 comments | 17 Oct 25 07:18 UTC | HN request time: 0s | source

GPT-5 seems stronger at generating diverse ideas, pros/cons, and perspectives, while Sonnet 4.5 feels better at decision-making and writing code. Has anyone tried running them together in Claude Code? Did it improve results?

Show context

covil ◴[17 Oct 25 07:23 UTC] No.45614108[source]▶

>>45614084 (OP) #

I'm asking claude code to collaborate with codex. You can do it by adding codex as a mcp server. They added `codex mcp-server` command for user to use codex as a mcp server recently. And it did improve the plan and code quality; I ask it to review the plan and generated code. Full command is like this: `claude mcp add codex -- codex mcp-server`

replies(1): >>45614372 #

1. iosifnicolae2 ◴[17 Oct 25 08:16 UTC] No.45614372[source]▶

>>45614108 #

Nice. I will give it a try. thx

↑

Ask HN: Claude Code with Multiple Models?