And every comment on HN calling out vibe-coded slop has this same complaint comment in turn. OP has an actual complaint, your complaint is just "stop complaining".
I'd be interested to see if using DiffusionGemma-as-Jev helps as you can feed the image directly into the model and it'll make decisions based on the image embeddings.
I had a long talk with chat gpt about this today as well. I think its duable and prolly not too hard either, also you could do lotsa funky stuff with stitched frames of a video in one 4x4 grid for example and send that as one image for analysis. that way temporal understanding can be had for fractions of a second by jev... also because vlm works in pixel space you can get around the whole state machine issue as well, so many possibilities...
Curious about people’s experience here. I am working on a small model, verify by jev, and escalate to big model. Some cases, the small model is not a model but some regex.
I trailed off a few lines into the README. No human ever edited any of this. « LLM detected, project rejected ».
Every third post in HN has this same complaint comment. Everybody knows.
And every comment on HN calling out vibe-coded slop has this same complaint comment in turn. OP has an actual complaint, your complaint is just "stop complaining".
I stopped reading at “The honest caveat”…
I'd be interested to see if using DiffusionGemma-as-Jev helps as you can feed the image directly into the model and it'll make decisions based on the image embeddings.
I had a long talk with chat gpt about this today as well. I think its duable and prolly not too hard either, also you could do lotsa funky stuff with stitched frames of a video in one 4x4 grid for example and send that as one image for analysis. that way temporal understanding can be had for fractions of a second by jev... also because vlm works in pixel space you can get around the whole state machine issue as well, so many possibilities...
How does it do on OSWorld-verified? Recently read that even Fable 5 is just at 85% .
This probably throws a spanner in the wheels there:
> Every piece of reasoning the frontier model does for free has to be rebuilt here as deterministic state.
EDIT: Not to shit on this though. I totally believe that some smart mixture of LLM-reasoning + Jev-style + determinism is going to be pretty amazing.
Super cool. Hope waitlist will move soon. I have a use case for it too.
are you the author? If so - what are your notes on using Jev in this scenario?
Did you do the follow up questions? I was invited within a few hours of joining today.
It's also now on openrouter and cloudflare
Same here. 8h hours later I was in.
Curious about people’s experience here. I am working on a small model, verify by jev, and escalate to big model. Some cases, the small model is not a model but some regex.
cheap-confirm-escalate
Using jev as the confirm step.