>10x More Efficient Pretraining

(magic.dev)

60 points | by ronfriedhaber 2 days ago

9 comments

  • pvillano 51 minutes ago
    A lot of people are betting their money on infinite growth forever of AI performance, compute usage, user base, subscription price.

    I think cost will decrease forever.

    • bilater 39 minutes ago
      Cost will keep dropping, but the frontier will keep getting pushed. The whole "give me today's model 10x cheaper and I'm good" line is a fallacy. It isn't true now and it never will be for the top 1% of tasks, which will create the most economic gains.
      • adam_arthur 22 minutes ago
        There are an enormous number of tasks that can get by on good enough.

        If you need image recognition, and a 30B model saturates the use case with 100% accuracy, you absolutely wouldn't continue to use the next frontier model as they come out.

        And I'd argue most economically meaningful tasks will be saturated by cheaper models than those requiring frontier.

        Think about what today's models can do with pretty close to 100% accuracy, and then consider that they will be orders of magnitudes cheaper over the years.

        5.6 Sol can already obviate tons of labor, and why would you pay 2x or more for no meaningful gain?

        The relative gap between frontier and non frontier also continues to shrink, so it's not like you take a meaningful performance loss by rewinding to models from 3-6 months ago. And soon that gap will expand to 12-24 months.

        I get the impression the majority of people on here only think about coding, which net net will be a tiny volume of overall AI use in the end.

        • bilater 17 minutes ago
          That can all be true but the frontier models will still have a huge market. You're thinking of all tasks as a fixed pie. The top 1% of intelligence opens up a whole new pie, stuff nobody does today because it's too expensive: daily cancer scans instead of one every few years, asteroid mining missions that need ten thousand PhD-hours of planning, custom drugs designed for your specific tumor, a personal lawyer and doctor for every person on earth, auditing every line of code in every bank and hospital continuously and so on.
          • adam_arthur 11 minutes ago
            Yes, agree that token consumption will increase exponentially for the next while.

            Disagree that the frontier model is where the economic gains will be realized.

            The smaller the relative gap between frontier and non-frontier/open weights, the less pricing power.

            This gap has shown only to shrink over time, not expand.

            Businesses will pay more for frontier, but not meaningfully more to justify the economics. It's always going to be a low margin business, perhaps outside of cyber security, warfare/intelligence and perhaps drug discovery.

            Though the expensive and time consuming part of drugs is doing the trials and getting approval, not coming up with ideas

          • michaellee8 10 minutes ago
            yea you see no body are vibecoding games before opus 5 and astra, after they are released games basically got commoditized
            • adam_arthur 5 minutes ago
              If the output is commoditized, how much can you afford to pay for the input?
      • saulpw 22 minutes ago
        I think there's an intelligence limit, or at least asymptote. It may be above human intelligence, but I don't think it's miles above it (at least not the kind of intelligence humans can create, recognize, or use). For example in Go, most estimates place God or "perfect play" three ranks above top professionals[0]. In the latest human-AI Go match, the human got a 2 stone handicap. So it's not like we have a lot more frontier to push there.

        [0]https://senseis.xmp.net/?HandOfGod

  • simonw 1 hour ago
    > We match DeepSeek V4 Pro Base using ~50x fewer FLOPs – that’s around half of GPT3’s pretraining compute, or ~$0.5M on GB200.

    If this holds up that's a really big deal.

  • ansk 44 minutes ago
    I don't know enough about the specific models they're comparing against to say this definitively, but it looks to me like they're comparing their pre-trained models with others' post-trained models.

    The metric upon which their 10x claim is based (bits-per-byte) is exactly the metric which is optimized during pre-training. Post-trained models are fine-tuned to optimize other metrics, which is known to be detrimental to performance on bits-per-byte evaluations. So bits-per-byte evaluations will always make a pre-trained model look favorable in comparison to a comparable model which has also undergone post-training.

    Can someone confirm whether the models they are comparing against (DeepSeek V4, Kimi K2, and Nemotron 3 Ultra) have been post-trained?

    • brrrrrm 37 minutes ago
      they say they're looking at base models, so I think it's fairly compared as written.
  • brrrrrm 34 minutes ago
    this is basically the only thing pre-training teams work on in labs. compute efficiency is the metric, the assumption that scaling = intelligence is considered a given.
  • FailMore 1 hour ago
    If you're like me, a SWE who is curious about ML/LLM training but unfamiliar with the terms, I got an agent to explain to me how to read the charts.

    Basically, you can think of a LLM as a function which generates a probability distribution of words. If the next word in a series is "they", and one model predicts that word 40% of the time, and another model predicts that word 1% of the time, the latter model is worse as it is more surprised by the true distribution.

    You can convert these probabilities into "bits":

    surprise in bits = −log₂(probability of the actual token)

      Probability of actual token,Surprise
      1,0 bits
      1/2,1 bit
      1/8,3 bits
      1/1024,10 bits
    
    This is then normalised by text length:

    Bits per byte = total next-token surprise in bits / number of bytes in the evaluated text

    So the lower you go on the charts, the less surprises in the LLMs distribution (a better model).

    For more info: https://smalldocs.org/s/DfvdGuFsiR3LlzXw1H5J0K#k=AJ8V1AQECYj...

    • asadm 48 minutes ago
      not a good enough submarine
  • ismael_rr 1 hour ago
    Super awesome. Wish they would release the paper about what they did to achieve this. I remember nous released the token superposition paper which improved pretraining FLOPs some, but not 50x: https://nousresearch.com/token-superposition. Wondering if they also found some cool tokenization strategiesa
  • monneyboi 1 hour ago
    Imagine the sheer amount of power you could save by releasing the paper.
    • speedgoose 1 hour ago
      But thanks to the Jevon Paradox, the global power consumption would probably increase.

      https://en.wikipedia.org/wiki/Jevons_paradox

      • aaroninsf 33 minutes ago
        Solar is now not only the cheapest energy it's cheaper to intitially deploy than non-renewables.

        Doesn't mean we should waste energy; it does mean that we have crossed a threshold beyond which energy concerns change shape.

  • vatsachak 1 hour ago
    Cool story. If it's true the company will be bought by open AI/Anthropic and Chinese labs will discover the trick and open source it by next quarter.
  • mohsen1 15 minutes ago
    [dead]