Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

janalsncm 2 hours ago | parent | next [-]

I really feel out of my depth because 2 out of the 3 methods here seem like they shouldn’t work?

> To evaluate comprehensibility quantitatively, we employ an LLM-as-a-Judge framework

This isn’t the worst idea, but it’s still a bit incestuous. Adding an LLM judge to check for hallucinations creates two new kinds of problems: false positives, where your judge hallucinates an incorrect fact, and false negatives, where the judge lets a hallucination slip by.

> We measure reproducibility through knowledge distillation. By fine-tuning a weaker model on the generated CoT traces, we use the downstream performance gain of the student as a proxy.

And my problem here, as a member of the GPU proletariat, is that this just seems incredibly inefficient. In other words, you’re going to generate a bunch of rollouts from your model then wait for the student to train? I guess if you have the compute to train a trillion params then maybe you don’t care.

	▲	arcanemachiner an hour ago \| parent [-]
		I have my LLM agents fact check each other as a matter of course. They each regularly find things that the other missed. They are typically the same model (Opus).

▲

plastic-enjoyer 5 hours ago | parent | prev [-]

> scaling to 1T parameters significantly enhances sample efficiency and performance ceilings;

Man, I find SOTA deep learning somewhat hilarious. We scale models to absurd proportions, burning through a shitload of resources just to achieve (slightly above) human intelligence. The human brain has a few billion neurons and uses as much power as a light bulb.

▲

pfdietz 4 hours ago | parent | next [-]

The human brain is estimated to have approaching 10^11 neurons (most of them in the cerebellum).

However, a neuron is much more than a single parameter. The brain is estimated to have from 10^14 to 5x10^14 synapses.

▲

fallingfrog 3 hours ago | parent [-]

True although a lot of those neurons and synapses are in the cerebellum, responsible for motor coordination and or in the visual cortex and so forth. Only a portion are in the language and reasoning areas. LLM's are comparable to human scale now, i think, and if trends continue will swiftly pass us by in the future.

If I had a magic button I would not only pause AI development but set it back 10 years. Sadly I have no influence on events and those who do, don't care about the future of humankind or actively wish us dead.

	▲	Alpha3031 2 hours ago \| parent [-]
		More recent research suggests the cerebellum does actually have a significant role in cognition. See for example https://pmc.ncbi.nlm.nih.gov/articles/PMC4089997/ and https://www.sciencedirect.com/science/article/pii/S138904172....

▲

mapontosevenths 2 hours ago | parent | prev | next [-]

This is the worst they will ever be.

In 1956 a 5mb hard drive shipped on a large truck and took a team of men to unload. It consumed huge amounts of power, and cost about $3,200/month to run. In today's dollars that would be about $160,000 per month.

Aren't you glad we didnt just give up because it was kind of expensive?

▲

aziis98 4 hours ago | parent | prev | next [-]

When for the training part you have to consider brains had like billions of years to develop. Maybe one of the reasons llms seem to be so expensive to train is because we are "compressing" in far less time that learning part

	▲	ziofill 3 hours ago \| parent [-]
		I think it’s more accurate to say that the mechanism that grows a brain had millions of years to develop.

▲

esikich 4 hours ago | parent | prev | next [-]

Similarly, all the components in an audio amplifier are super dumb because you can just have 4 guys play in your living room amirite

▲

Eridrus 4 hours ago | parent | prev | next [-]

Do you find cars similarly hilarious?

	▲	colordrops 3 hours ago \| parent [-]
		Yes

▲

retinaros 3 hours ago | parent | prev | next [-]

everything in LLM world is that right now.

▲

yieldcrv 4 hours ago | parent | prev [-]

the active layers concept seems to be experiencing convergent evolution to how synapses in a human function

huge parameter models with many small but efficient layers can work quickly on low resource hardware

similar to how neurons experience chemical spiking to activate small portions of the brain at once