xlightmoonx

xlightmoonx

xlightmoonx

xlightmoonx

xlightmoonx

Kstov, more interesting footage 🔥😊

But who leaked Ava Peace videos, people are really... Bad watch them belowshow more

AI has had exactly two scaling axes that worked... so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inferenceshow more

Somali reps are now endorsing Amy Acton for Ohio... Governor in Somali This should tell you everything you need to know on who Amy actually represents….show more

WTF IS THIS 😭

Them catch Sabinus Dey check he sportybet game😂😂😂

Eyes on you🫶🏻 #OASISxJoongDunk #OASISGentleEscapeMomentwithJoongDunk

NOW THAT HALLOWEEN IS OFFICIALLY OVER.

It’s not just rubber. It’s an experience. Something completely... new. And I absolutely loved it! A dream that came true. 🖤show more

when he has a short hair and full beard >>

She jiggles it effortlessly🤍

My favorite part of this Kathy Hochul video is... that the Halal guy is covering his face because he’s here illegally.show more

What a throw by CJ Stroud

this is how it looks when I say "just... one more day" to these socks. that smell, pheewshow more

When I go to the farm shop and all... they have is homogenised semi-skimmed milk in plastic bottles, no raw-milk cheeses and bacon I could buy at the local chain supermarket.show more

Billie for YOUR TURN II