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.
And everyone compares their price / task against Opus 5.5 Max in their comparison charts, barely anyone benches against Medium which really is the sweet spot for speed and competency.
The first time I tried to use fable 5.2 it made a bunch of really amateurish technical design assumptions about my project that cursory reading of docs would have disproven (but also should have just been discarded because of taste reasons anyway). I switched back to Opus 5.5 after that.
Re:Gemini 4 Neon
by pjankiewicz on Wednesday November 18, 2026 @05:22PM
(#50553113)
I agree Opus 5.5 is something different entirely. It is even hard to find tasks for other agents to be honest where you know the results will be picked apart when Opus 5.5 reviews them. In my setup Opus 5.5 uses codex from time to time when I'm running out of credits and it decided to run 2 astra agents for the same task to improve its performance.
No wonder they went for the 5.5 naming, instead of the .1 increase. From just the benchmarks, it seems like neon is basically on par with Opus 5.5 which came out 2 months ago.