News for hackers. Stuff that matters.

A comment on Opus 4.5 is not the normal AI agent experience that I have had thus far. Parent comment

Re:Opus 4.5 is not the normal AI agent experience that I hav... by theanonymousone on Tuesday January 06, 2026 @01:26PM (#46516373)
Is Claude "Code" anything special,or it's mostly the LLM and other CLIs (e.g. Copilot) also work?
[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by square_usual on Tuesday January 06, 2026 @01:40PM (#46516579)
I've tried most of the CLI coding tools with the Claude models and I keep coming back to Claude Code. It hits a sweet spot of simple and capable, and right now I'd say it's the best from an "it just works" perspective.
[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by speedgoose on Tuesday January 06, 2026 @05:01PM (#46519479)
It’s mostly the model, Copilot, Claude Code, OpenCode, snake oil like Oh My OpenCode, it’s not huge differences.
[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by troupo on Tuesday January 06, 2026 @05:30PM (#46519744)
Claude Code seems to package a relatively smart prompt as well, as it seems to work better even with one-line prompts than alternatives that just invoke the API.

Key word: seems. It's impossible to do a proper qualitative analysis.

[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by pluralmonad on Wednesday January 07, 2026 @05:49PM (#46534338)
Why do you call Oh My OpenCode snake oil?
[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by kaydub on Wednesday January 07, 2026 @01:22PM (#46530307)
In my experience the CLI tool is part of the secret sauce. I haven't tried switching models per each CLI tool though. I use claude exclusively at work and for personal projects I use claude, codex, gemini.
[ Parent | on HN ]