Rendered at 01:07:42 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
imranq 5 hours ago [-]
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.
jwpapi 5 hours ago [-]
I think it can make a lot of sense to make a set with jev and then train laya on that set and do the rest with laya for saving $
putna 5 hours ago [-]
agree, too good to be true for one shot cases
PaulRobinson 8 hours ago [-]
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.
ipsi 6 hours ago [-]
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.
Izmaki 5 hours ago [-]
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".
bigyabai 37 minutes ago [-]
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.
mynegation 30 minutes ago [-]
Uh, my clipboard says 20 years
frag 8 hours ago [-]
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
Stay tuned ;)
putna 5 hours ago [-]
cool, will check it
bigyabai 7 hours ago [-]
It won't. Laya is a finetuned version of Google's BeRT model, which is almost 10 years old right now.
If BeRT had any potential to disrupt the datacenter buildout, it already would have.
viraptor 4 hours ago [-]
Modernbert is from 2024. It's also trained from scratch, not a fine tune.
speedping 3 hours ago [-]
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
altano 6 hours ago [-]
How much memory does this use of the test machine's (M3 Max) 128 GB unified memory?
ImJasonH 17 minutes ago [-]
I had Fable one-shot the same demo from the same weights on an iPhone 15 Pro and it decides in ~40ms.
WASDx 6 hours ago [-]
The model is only 0.3B params so probably not much.
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.
putna 3 hours ago [-]
agree, maybe os jev is too strong of a wording.
when more people get the idea how to create system one, I am sure Laya will have lots of use cases.
brcmthrowaway 56 minutes ago [-]
Why is Laya being shilled here? It doesn't have real intelligence backing it.
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.
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.
Stay tuned ;)
If BeRT had any potential to disrupt the datacenter buildout, it already would have.
[1]: https://github.com/mizorewww/laya-coreml
when more people get the idea how to create system one, I am sure Laya will have lots of use cases.