Hacker News new | past | comments | ask | show | jobs | submit
Same here. Spin up a few long horizon tasks, have it manage the whole thing as a project, you can talk to it, interrupt it, engage in side-quests, its like talking to a human.

Have another session on another machine (say, IOS build on a mac, and server build on a linux?). No problem, they will happily coordinate with each other through the /remote-control protocol, and then you feel like you are in a crowd, with those sessions talking to each other and over you.

No such feel with OpenAI nor Google models for me. They are absolutely great for lots of things, but nothing comes close to the feel of Opus 5.5 and Fable.

(I am biased; i mainly use the anthropic models so i got used to them).

I dont even feel like fable 5.2 is better. Imho the best model rn is Opus 5.5 MEDIUM.
loading story #50555272
loading story #50553393
I had the opposite experience.

I had subscription to both anthropic and openai. I was out of credits for openai, so used anthropic to fix some coding issues. Spent whole weekend prompting while it kept failing over and over. Finally on Monday I had openai's weekly quota start, 2 hours issue was done.

The same thing happened again, after a couple weeks. Two weekends wasted trying to make Anthropic models to behave.

loading story #50557983
fable 5.1 was strictly worse than opus 5.5 (which was embarasing). Even Fable 5.2 is slightly better, but both slower and more expensive. Again, pound for pound Opus 5.5 from 2 months ago is still probably one of the best models.
loading story #50557992