Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) and Vibe CLI

Re:Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) an... by xmcqdpt2 on Wednesday December 10, 2025 @12:43AM (#46214491)

I think the problem is that models are just not that good yet. At least for my usage at work, the CLI tools are the fastest way to get something useful, but if you can't describe basically exactly what you want, you get garbage.

[ Parent | on HN ]

Re:Mistral Releases Devstral 2 (72.2% SWE-Bench Verified) an... by embedding-shape on Wednesday December 10, 2025 @06:59AM (#46216761)

They are good enough, but people aren't exploring other UIs enough. The TUI tools (which I think you're referring to, Codex, Claude Code et al) are a good start, but they feel like a prototype compared to a completely different UI. You'd still describe what you want, but not imperative in a chat window, but some other manner.

[ Parent | on HN ]