Local LLMs are the future, and one of the reasons I think the data centre furore is just going to end in a market crash.
LLMs that can reliably be used for control problems are the future, and I think classic/deep RL has generally been overlooked for years for a whole host of problems by wider industry because it felt inaccessible. The first thing I thought of when I saw Jev (and then Laya), was "this might move the needle in a really, really interesting way".
Local LLMs that can reliably be used for control problems smash through a lot of barriers I'm interested in, and this intrigues me a lot. Guess I'm about to become a big Laya fan if it can run on this kind of hardware to this performance.
that's not a local LLM. If it's local, it doesn't matter in this case. Laya is a System 1 "AI", namely works like a classifier, given a state and questions, it shoots probabilities for each. I publish an episode tomorrow about Laya and Typesafe AI on https://www.youtube.com/@DataScienceatHome
The future for whom? The general public? Not a chance, no way, not unless it's able to run on a phone (anywhere from 20-40% of internet users, world-wide, are phone-only).
For companies? I think that's a lot more plausible, as that's mostly just a question of money - is it cheaper to run and administrate our own models, or outsource that?
For technically inclined users? I think that's unlikely unless they're able to operate on relatively cheap hardware while still being just as good as the hosted models. And by that I don't mean "a mac studio," that's far more money than I think is reasonable. A single RTX 5080, maybe, once memory prices start to drop.
Compare the games your average high-end smartphone can run to the AAA titles of the 2010's. It's not a matter of "unless it is able to" but "when it is able to".
That's going from 150w 720p gaming to ~15w 720p gaming in ~10 years. Let's say an inference cluster draws 1500w to deliver a small-ish 500b model at reasonable speeds/quantization.
Extrapolating from your gaming example, it will take smartphones only... *checks clipboard* ...100 years to achieve datacenter-level performance at the pace of 2010's improvements.
Based on my admittedly limited research, it seems like you should use Laya for much more deterministic tasks where you have some training data. It won't be as good as Jev for zero shot cases.
I did that on a little macbook m4 last night on my model of the innate immune system—fine tuning took 15m or so. Just wish it had a larger context window
Isn't part of the Jev marketing that it has "terra-class intelligence"? I don't know how much it actually achieves that, but unless that's EXTREMELY wrong, it's hard to see how a 0.3B model could claim to be an OS Jev.
Jevs marketing has a lot to do with claiming credit for this pardigm, when the devloper of Layla was actually the first to do it. Its quite annoying to see another member of the OpenAI mafia so clearly rip off someone elses IP.
What we should be talking about how Jev is actually closed source Layla.
So cool. I've fired up pumas (energy monitor) and it seems to run almost fully on the neural engine and not the GPU so it plays really nicely with CoreML
32 comments
[ 0.23 ms ] story [ 38.5 ms ] threadLLMs that can reliably be used for control problems are the future, and I think classic/deep RL has generally been overlooked for years for a whole host of problems by wider industry because it felt inaccessible. The first thing I thought of when I saw Jev (and then Laya), was "this might move the needle in a really, really interesting way".
Local LLMs that can reliably be used for control problems smash through a lot of barriers I'm interested in, and this intrigues me a lot. Guess I'm about to become a big Laya fan if it can run on this kind of hardware to this performance.
Stay tuned ;)
To me it’s like a solution looking for a problem that is already solved.
If BeRT had any potential to disrupt the datacenter buildout, it already would have.
For companies? I think that's a lot more plausible, as that's mostly just a question of money - is it cheaper to run and administrate our own models, or outsource that?
For technically inclined users? I think that's unlikely unless they're able to operate on relatively cheap hardware while still being just as good as the hosted models. And by that I don't mean "a mac studio," that's far more money than I think is reasonable. A single RTX 5080, maybe, once memory prices start to drop.
Extrapolating from your gaming example, it will take smartphones only... *checks clipboard* ...100 years to achieve datacenter-level performance at the pace of 2010's improvements.
What we should be talking about how Jev is actually closed source Layla.