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 mcny on Tuesday January 06, 2026 @01:20PM (#46516279)
Everybody says how good Claude is and I go to my code base and I can't get it to correctly update one xaml file for me. It is quicker to make changes myself than to explain exactly what I need or learn how to do "prompt engineering".

Disclaimer: I don't have access to Claude Code. My employer has only granted me Claude Teams. Supposedly, they don't use my poopy code to train their models if I use my work email Claude so I am supposed to use that. If I'm not pasting code (asking general questions) into Claude, I believe I'm allowed to use whatever.

[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by spaceman_2020 on Tuesday January 06, 2026 @01:22PM (#46516312)
What's even the point of this comment if you self-admittedly don't have access to the flagship tool that everyone has been using to make these big bold coding claims?
[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by hu3 on Tuesday January 06, 2026 @01:36PM (#46516520)
isn't Claude Teams powerful? does it not have access to Opus?

pardon my ignorance.

I use GitHub Copilot which has access to llms like Gemini 3, Sonnet/Opus 4.5 ang GPT 5.2

[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by halfmatthalfcat on Tuesday January 06, 2026 @01:24PM (#46516351)
Because the same claims of "AI tool does everything" are made over and over again.
[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by spaceman_2020 on Tuesday January 06, 2026 @01:32PM (#46516466)
The claims are being made for Claude Code, which you don't have access to.
[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by mr_mitm on Tuesday January 06, 2026 @03:53PM (#46518559)
I believe part of why Claude Code is so great because it has the chance to catch its own mistakes. It can run compilers, linters, browsers and check its own output. If it makes a mistake, it takes one or two extra iterations until it gets it right.
[ Parent | on HN ]
Re:Opus 4.5 is not the normal AI agent experience that I hav... by fragmede on Tuesday January 06, 2026 @01:35PM (#46516509)
It's not "AI tool does everything", it's specifically Claude Code with Opus 4.5 is great at "it", for whatever "it" a given commenter is claiming.
[ Parent | on HN ]