Rendered at 21:34:05 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
jwpapi 1 hours ago [-]
This is very interesting and the biggest glimpse of hope I’ve seen the last couple months here. I haven’t really paid attention to Fusion even though I got the email. I didn’t even assume it would be comparable.
JumpCrisscross 21 minutes ago [-]
I’m so confused. The top fusion is Fable 5 and GPT 5.5. That is not an “ensemble of weaker AI models.”
maniacwhat 16 minutes ago [-]
What its saying is if you look at any single model, it can be beaten by an ensemble of weaker models.
E.g fable 5 is beaten by an ensemble of previous gen models.
JumpCrisscross 12 minutes ago [-]
I guess so. 4.8 + 4.8 > Fable 5 is interesting, though not particularly game changing. (The others all fuse frontier models. Which is an argument for using those frontier models more. Not less.)
tim-star 18 minutes ago [-]
i guess the point is that any fusion is better than any single model and a fusion of the top two models is obviously the best?
for cost though i guess you could just duct tape together 10 open source models and then thats comparable?
JumpCrisscross 13 minutes ago [-]
> though i guess you could just duct tape together 10 open source models and then thats comparable?
This is what I was hoping to see data for.