Hacker News Reader

Comment by aurareturn | Hacker News Reader

This is truly the biggest breakthrough from DeepSeek - that an LLM can teach itself to reason, no human feedback needed.

That’s nuts and brings forward the idea that an AI is close to self improvement.

View on HN

It’s great, but it only works for problems where there is exactly one correct solution and it’s possible to automatically verify the solution - like math and programming. So far these reasoning models have not shown much transfer learning of reasoning to other domains, and are often worse at non-math/code tasks than standard models.

Not sure if this a trivial or naive thought - is that perhaps because in non-discrete ideas there is more granularity of information encoded compared to a numerical solution?

Separatelt, but on a related note - do we need analog or quantum computing to "truly" scale?

To ”truly” scale we need a system directly doing calculation on some fundamental property of matter. Quantum computing is _close_ but suffers from a lack of interpretability: how would we know if our quantum simulation of the universe would include the quantum computer doing the simulation, as well as another recursive copy of the simulation, and another, and another…

There are infinite solutions to coding problems.

You could have lots of comments and pass statements and unnecessary conditionals.

I don't think it matters that there is only one correct answer.

It matters that you can verify reliably if the answer is correct enough.

So, we have a very good left-brain model.

We can probably make it work at more nebulous problems by using a big LLM to judge the quality of the answers as well. It should be easier to recognise e.g. a really good poetic translation than to make one, and as long as that's true it could benefit from internal monologue "reasoning" in those domains as well.

This has been done, and doesn't work especially well. See, for example, GANs, which are difficult to train and vulnerable to mode collapse.

Not saying that it's impossible, but reinforcement learning of the form shown by DeepSeek was particularly well-established and robust. It's sort of ironic, actually...IIRC, OpenAI started in the world of this kind of reinforcement learning.

LLMs can verify math problems if you give it a calculator tool. Coding problems if you give it a Linux environment.

So why can’t we give LLMs other virtual environments to verify if the solution is correct? For example, a stock simulator, a physics simulator, a driving simulator, etc.

Because simulations are not perfect models. A particle physics simulation simply cannot be accurate enough to provide the 5-sigma (99.99994%) confidence typically required in particle physics. Not even measurement is simple when the requirements are so strict, that’s why they spend billions building those huge accelerators.

Once the computer learns to apply the logic of Tic-Tac-Toe to Global Thermonuclear War, we will finally have the W.O.P.R.[0]

[0]https://en.wikipedia.org/wiki/WarGames

We already knew that kind of stuff from AlphaZero vs AlphaGo

AlphaGo Zero is a version of DeepMind's Go software AlphaGo. AlphaGo's team published an article in Nature in October 2017 introducing AlphaGo Zero, a version created without using data from human games, and stronger than any previous version.[1] By playing games against itself, AlphaGo Zero: surpassed the strength of AlphaGo Lee in three days by winning 100 games to 0; reached the level of AlphaGo Master in 21 days; and exceeded all previous versions in 40 days.[2]

Training artificial intelligence (AI) without datasets derived from human experts has significant implications for the development of AI with superhuman skills, as expert data is "often expensive, unreliable, or simply unavailable."[3] Demis Hassabis, the co-founder and CEO of DeepMind, said that AlphaGo Zero was so powerful because it was "no longer constrained by the limits of human knowledge".[4] Furthermore, AlphaGo Zero performed better than standard deep reinforcement learning models (such as Deep Q-Network implementations[5]) due to its integration of Monte Carlo tree search. David Silver, one of the first authors of DeepMind's papers published in Nature on AlphaGo, said that it is possible to have generalized AI algorithms by removing the need to learn from humans.[6]

Google later developed AlphaZero, a generalized version of AlphaGo Zero that could play chess and Shōgi in addition to Go.[7] In December 2017, AlphaZero beat the 3-day version of AlphaGo Zero by winning 60 games to 40, and with 8 hours of training it outperformed AlphaGo Lee on an Elo scale. AlphaZero also defeated a top chess program (Stockfish) and a top Shōgi program (Elmo).[8][9]

Source: https://en.wikipedia.org/wiki/AlphaGo_Zero

Indeed. But DeepSeek is the first to release a working repro for LLMs as far as I know.

Yeah but LLM and game AIs are very different. An AI can easily tell if it won the game but an LLM can't know by itself if what they said was useful.

A physics simulator's rules will be derivative of known physics. If we ask it to push the boundaries of known physics, then we can't verify it without real-world experiment. Absent that then it's basically Chegg on steroids: "Tell me, based on what we believe about how the universe works, about X." is the implicit preface to every physics question.

To the extent that someone can figure out a way out of this epistemic box, I'm interested.

This makes ScaleAI obsolete right?

Reply on news.ycombinator.com