So we can just make posts with any titles like that now? Look, I understand the optimism in open-weight models, but this headline is, well, far from reality. This repo has a lot of huge claims with a lot of amazing scores in the table, but zero proof.
As I understand, the code part is in https://github.com/Tiger3807861189/J-Space-Cognition-Suite-V... but there's nothing there that would make V4 Pro perform as well as Fable, it's mostly prompting - that's not even a proper implementation of "J-Space".
The repo gave you guide and benchmark of how to tweak ds4 pro for better performance (with clickbait title: Fable 5 level), what kind of more proof do you require? More benchmarks? Reports for media outlets? STF model on HF?
I find it very intriguing. I reminds me of the insight in the early days that prompting the models to "think step by step" gave big performance boosts. Here we basically tell the models "You have an internal monologue/J-space and you can use it!". Quasi an opaque 'think step by step' prompt. The models were always able to think step by step but needed to be prompted to do so. Maybe the same thing is possible with the J-Space? The huge claims are yet to be replicated/proven, though.
4 comments
[ 0.31 ms ] story [ 20.8 ms ] threadAs I understand, the code part is in https://github.com/Tiger3807861189/J-Space-Cognition-Suite-V... but there's nothing there that would make V4 Pro perform as well as Fable, it's mostly prompting - that's not even a proper implementation of "J-Space".
The repo gave you guide and benchmark of how to tweak ds4 pro for better performance (with clickbait title: Fable 5 level), what kind of more proof do you require? More benchmarks? Reports for media outlets? STF model on HF?