Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Mercury: Commercial-scale diffusion language model

inceptionlabs.ai

Post reply on HN
Print view View original

21–30 of 189 posts

Re: Mercury: Commercial-scale diffusion language model

#21

Post by scratchyone »

orbital-decay wrote: post #11
parsimo2010 wrote: post #8

This sounds like a neat idea but it seems like bad timing. OpenAI just released token-based that beats the best diffusion image generation. If diffusion isn't even the best at generating images, I don't know if I'm going to spend a lot of time evaluating it for text. Speed is great but it doesn't seem like other text-based model trends are going to work out of the box, like reasoning. So you have to get dLLMs up to t…

Does it beat them because it's a transformer, or because it's a much larger end-to-end model with higher quality multimodal training?

I wonder if it benefits because it can attend to individual tokens of the prompt while generating, compared to typical diffusion models that just get a static vector embedding of the prompt.

Re: Mercury: Commercial-scale diffusion language model

#22

Post by amelius »

inerte wrote: post #7

Not sure if I would tradeoff speed for accuracy. Yes, it's incredible boring to wait for the AI Agents in IDEs to finish their job. I get distracted and open YouTube. Once I gave a prompt so big and complex to Cline it spent 2 straight hours writing code. But after these 2 hours I spent 16 more tweaking and fixing all the stuff that wasn't working. I now realize I should have done things incrementally even when I hav…

Wouldn't it be possible to trade speed back for accuracy, e.g. by asking the model to look at a problem from different angles, let it criticize its own output, etc.?

Re: Mercury: Commercial-scale diffusion language model

#26

Post by ris »

marcyb5st wrote: post #6

Super happy to see something like this getting traction. As someone that is trying to reduce my carbon footprint sometimes I feel bad about asking any model to do something trivial. With something like that perhaps the guilt will lessen

Please see yesterday's https://simonwillison.net/2025/Apr/29/chatgpt-is-not-bad-for... instead of propagating the hand-wringing.

Re: Mercury: Commercial-scale diffusion language model

#27

Post by adammarples »

jonplackett wrote: post #5

Ok. My go to puzzle is this: You have 2 minutes to cool down a cup of coffee to the lowest temp you can You have two options: 1. Add cold milk immediately, then let it sit for 2 mins. 2. Let it sit for 2 mins, then add the cold milk. Which one cools the coffee to the lowest temperature and why? And Mercury gets this right - while as of right now ChatGPT 4o get it wrong. So that’s pretty impressive.

If you let it sit for 2 minutes your time is up and you don't have time to add the cold milk

Re: Mercury: Commercial-scale diffusion language model

#28

Post by orbital-decay »

nullc wrote: post #15
byearthithatius wrote: post #4

Interesting approach. However, I never thought of auto regression being _the_ current issue with language modeling. If anything it seems the community was generally surprised just how far next "token" prediction took us. Remember back when we did char generating RNNs and were impressed they could make almost coherent sentences? Diffusion is an alternative but I am having a hard time understanding the whole "built in…

Consider the entropy of the distribution of token X in these examples: "Four X" and "Four X and seven years ago". In the first case X could be pretty much anything, but in the second case we both know the only likely completion. So it seems like there would be a huge advantage in not having to run autogressively. But in practice it's less significant then you might imagine because the AR model can internally model th…

Diffusion models are built around this type of internal lookahead from the start (accurate near prediction, progressively less accurate far prediction, step forward, repeat). They just do it in the coarse-to-fine direction, i.e. in a different dimension, and had more thought put into shortcuts and speed-accuracy tradeoffs in this process. RL is also used with both types of models. It's not immediately obvious that one must necessarily be more efficient.

Re: Mercury: Commercial-scale diffusion language model

#29

Post by XenophileJKO »

inerte wrote: post #7

Not sure if I would tradeoff speed for accuracy. Yes, it's incredible boring to wait for the AI Agents in IDEs to finish their job. I get distracted and open YouTube. Once I gave a prompt so big and complex to Cline it spent 2 straight hours writing code. But after these 2 hours I spent 16 more tweaking and fixing all the stuff that wasn't working. I now realize I should have done things incrementally even when I hav…

So my personal belief is that diffusion models will enable higher degrees of accuracy. This is because unlike an auto-regressive model it can adjust a whole block of tokens when it encounters some kind of disjunction.

Think of the old example where an auto regressive model would output: "There are 2 possibilities.." before it really enumerated them. Often the model has trouble overcoming the bias and will hallucinate a response to fit the proceeding tokens.

Chain of thought and other approaches help overcome this and other issues by incentivizing validation, etc.

With diffusion however it is easier for the other generated answer to change that set of tokens to match the actual number of possibilities enumerated.

This is why I think you'll see diffusion models be able to do some more advanced problem solving with a smaller number of "thinking" tokens.

Re: Mercury: Commercial-scale diffusion language model

#30

Post by g-mork »

inerte wrote: post #7

Not sure if I would tradeoff speed for accuracy. Yes, it's incredible boring to wait for the AI Agents in IDEs to finish their job. I get distracted and open YouTube. Once I gave a prompt so big and complex to Cline it spent 2 straight hours writing code. But after these 2 hours I spent 16 more tweaking and fixing all the stuff that wasn't working. I now realize I should have done things incrementally even when I hav…

The excitement for me is the implications for lower energy models. Tech like this could thoroughly break the Nvidia stranglehold at least for some segments
Post reply on HN