News for hackers. Stuff that matters.
Re:Opus 4.5 is not the normal AI agent experience that I hav... by magicalist on Tuesday January 06, 2026 @11:02PM (#46522418)
So "pretty good at picking up existing codebases" so long as the existing codebase is all microservices.
Re:Opus 4.5 is not the normal AI agent experience that I hav... by heartbreak on Tuesday January 06, 2026 @11:36PM (#46522604)
Or a Rails app.
Re:Opus 4.5 is not the normal AI agent experience that I hav... by enraged_camel on Wednesday January 07, 2026 @02:17AM (#46523515)
I work with multiple monoliths that span anywhere from 100k to 500k lines of code, in a non-mainstream language (Elixir). Opus 4.5 crushes everything I throw at it: complex bugs, extending existing features, adding new features in a way that matches conventions, refactors, migrations... The only time it struggles is if my instructions are unclear or incomplete. For example if I ask it to fix a bug but don't specify that such-and-such should continue to work the way it does due to an undocumented business requirement, Opus might mess that up. But I consider that normal because a human developer would also do fail at it.
Re:Opus 4.5 is not the normal AI agent experience that I hav... by aprilthird2021 on Wednesday January 07, 2026 @04:23AM (#46524295)
With all due respect those are very small codebases compared to the kinds of things a lot of software engineers work on.