Opus 4.5 is not the normal AI agent experience that I have had thus far

Re:Opus 4.5 is not the normal AI agent experience that I hav... by qingcharles on Wednesday January 07, 2026 @02:22AM (#46523543)

I had Opus write a whole app for me in 30 seconds the other night. I use a very extensive AGENTS.md to guide AI in how I like my code chiseled. I've been happily running the app without looking at a line of it, but I was discussing the app with someone today, so I popped the code open to see what it looked like. Perfect. 10/10 in every way. I would not have written it that good. It came up with at least one idea I would not have thought of.

I'm very lucky that I rarely have to deal with other devs and I'm writing a lot of code from scratch using whatever is the latest version of the frameworks. I understand that gives me a lot of privileges others don't have.

[ Parent | on HN ]

Re:Opus 4.5 is not the normal AI agent experience that I hav... by lomase on Wednesday January 07, 2026 @04:25AM (#46524304)

Can you show us that amazing 10/10 app?

[ Parent | on HN ]

Re:Opus 4.5 is not the normal AI agent experience that I hav... by qingcharles on Wednesday January 07, 2026 @11:47AM (#46528691)

It's a not very exciting C# command-line app that takes a PDF and emits it as a sprite sheet with a text file of all the pixel positions of each page :)

[ Parent | on HN ]

Re:Opus 4.5 is not the normal AI agent experience that I hav... by lomase on Friday January 09, 2026 @05:12AM (#46552144)

As always, the LLM crowd makes claims about 100% perfect app, and then never share the source code.

[ Parent | on HN ]

Re:Opus 4.5 is not the normal AI agent experience that I hav... by philipodonnell on Thursday January 08, 2026 @09:00AM (#46541040)

You should just need the AGENTS.md right?

[ Parent | on HN ]