Depends on project complexity. For one of my more complex projects, I exclusively use sol-high ... nothing below that works correctly.
For this however, a comparatively much simpler task, tarra-high works fine.
back
1 comments
Right now, sol-xhigh is my favorite model. I feel that Opus 5 is dumber than 4.8. Fable is too expensive to do anything (limit of $50, started a prompt at $25, ended up at $75, is bullshit, but at least it's "free credits").
DeepSeek is okay for random API-based stuff, as it's cheap.
Local open models running on a 5090 are hit or miss. I feel that most GGUFs/quants are awful...
I am still on Opus 4.8, with a custom built harness and it works very well even on multi-repos, across stack, deep changes. I also have a very solid test suite which is helping the coding agent a lot
Opus 5 degrades to word salad.
I wonder if it is because of watermarking.
Opus 5 doesn't really even speak coherent English. I'm not sure what's going on, but it can't explain anything. It still does an excellent job with code and writing tests and code review and creating and completing a plan, and it seems to be able to understand English instructions, but it sure as hell can't explain what it did or how to use the code it wrote.
That was true before they announced the watermarking, I'd already started to back off of using Opus as much because I like to understand what the model is doing and have it write documentation I can use to reproduce its results, but maybe watermarking was already in there unannounced.
This 100%. The incoherent drivel has literally made me move away from CC completely.
Agreed, I'll get a terminal full of text and I just reply "I don't understand this"
And it retypes it for a human, I'm doing this more and more lately.
Ah, so it's not only me :-D
I think it could be the watermarking, but at this point they might be deliberately complicating the prose so that we ask clarifying questions and that leads to more token spend.