Claude Opus is my current most favorite model. I had a few blissful months of using it. Generated some good PRs, got stuck in debug loops not as many times as with previous models. I ended up extending the spend limit multiple times.
Opus Cocktail Bar, Sofia
After burning through far too many tokens, I had to stop and think. Is my usage really appropriate? Is it worth thinking how much tokens each prompt consumes? Is it because of the MCPs? Why does it make all these API calls to my dev server? How much does all of that even cost? It’s not clear from the dashboard at all.
While I’m rethinking my life’s choices, I switched to Codex and GPT 5.2. I feel like between the 4 AI editors that I have, I may have enough agent time available to last until the end of the billing period.
Being stuck with one option is not ideal. The situation is not like I have to write code without agents but my overuse of Opus is giving me a glimpse into a future where these models may start costing as much as people.
Veselin.blog 
I’m curious what you are building? I haven’t used any of the AI models for anything beyond debugging or getting a quick script. It still feels very brittle and I have it hallucinate functions that don’t exist.
LikeLiked by 1 person
Everything. I decided that I would not write code but would use AI prompts about a year ago. At least 80% of my PRs are AI generated.
It hallucinates, makes up functions, generates broken markup. It insists on stupid solutions, reverts working code to replace it with broken code.
Despite that, it enables a completely different way of work. I no longer need to produce atomic commits with code that grows iteratively. I can jump between different approaches between two commits. It’s faster this way.
And it often nails the solution from the first prompt.
LikeLiked by 1 person