Settings

Theme

SubQ: a sub-quadratic LLM with 12M-token context

subq.ai

84 points by mitchwainer 15 days ago · 46 comments

Reader

2001zhaozhao 15 days ago

Assuming this is real and much better than existing linear attention methods as advertised, not launching with a technical report is a big miss.

Edit: their blog post (https://subq.ai/how-ssa-makes-long-context-practical) does go pretty in-depth about it

Edit 2: the fact that they're going straight for an end-to-end coding product on day 1 is very ambitious. Other speed/efficiency-oriented AI companies (Cerebras and Inception come to mind) still don't have a first-party coding product after years. IMO this is absolutely the right way to go if they really do have the big breakthrough they're claiming.

mohsen1 15 days ago

- magic.dev claimed 200M context window and it's been two years since and no real product yet.

- They are admitting that this is built on top of a Chinese model[1]

- They committed a huge chart crime with the Y axis of a chart comparing to Opus on their website that I can't find anymore (Too embarrassing to keep?). The delta between their score (81%) vs. Opus (87%) on SWE bench was hugely minimized

- They named the company subquadratic but in parts they said O(1) linear scaling. At O(1) you could do much more than 12M tokens context window. At O(log n) even.

I hope this is real but I doubt...

  • alexsubq 13 days ago

    The chart crime was not intentional! We will not make you wait two years. We are O(n), not O(1). O(1) would unfortunately be an impossibility. We may as well do infinite context at that point!

    • bbctr1 9 days ago

      What’s keeping you from releasing paper and access to the model?

      • alexsubq 9 days ago

        Model: - making sure it has been properly red-teamed, meets user preferences, etc. - it depends on what folks want in the model. Our original papers was mostly the technical blog post, but we decided to wait a little longer to see what else folks wanted and share more benchmarks

    • esafak 11 days ago

      Good luck.

  • pvtmert 11 days ago

    > not affiliated with subq,

    i see in the linked post they mention O(n) not O(1). O(1) would basically be impossible and instant. Something like no compute required, constant results...

    The name subquadratic is actually good and makes sense to me. Because today's models are usually O(n^2) or worse. Anything equals or less than O(n^1) is basically sub-quadratic.

    Meanwhile O(log n) would be logarithmic as the log name indicates. But we have a long way to go there. Maybe with double tokenizer plus extensive caching it may be possible...

    What I mean here is tokenizing the user input; then capturing intent; caching intent -> response. So that next time once you get the intent, you don't need to do full transformer inference compute. This can be logarithmic complexity in terms of time complexity.

  • artisin 15 days ago

    Ah, I nearly forgot about magic.dev. I took a quick peek to check up on them. Welp, last social/blog activity was in... 2024. But hey, their careers page still says they're hiring! So they must be doing just fine.

pstorm 15 days ago

I’m very surprised this isn’t getting more attention. Am I missing something?

It seems at or above SOTA on the given benchmarks, doesn’t have context rot, is orders of magnitude faster, and uses less compute that current transformer models. I suppose it’s just an announcement and we can’t test it ourselves yet.

  • alexsubq 15 days ago

    We are SOTA in some ways and not in others, continuously working to make it better! We need a little more time to scale, as we are working on things like disaggregated prefill, etc., the norms of large-scale model infra.

    I am happy to answer any questions!

    • supern0va 15 days ago

      This seems super cool if as described, but I'm sure you can understand the skepticism.

      Do you anticipate having any kind of public accessible chat interface for testing in the near future?

      Also, what, if any, benefits are there for smaller context windows? Is there still a material improvement in cost to serve under say 256k? I'm curious about the broader implications for the space beyond improvements for very large context windows.

      • alexsubq 14 days ago

        I do, for sure! Yes, we have a few product rollouts lined up. The differentials for latency are posted in our blog post, so that should provide an idea of where the scaling law differentials kick in.

    • dirtyalt 14 days ago

      I have questions.

      Can you back up your claims?

      Why did you not release the white paper in parallel with the product?

      Feels really fishy.

      • lelanthran 11 days ago

        In this new knowledge economy, there is no benefit to publishing your secret sauce.

        If I came up with a novel thing I'd monetise it first, because publishing it makes it part of the training that adds value to billion dollar corps with zero credit to me.

        In the old knowledge economy I benefited from the credit assigned to me.

        So, to me, nothing fishy at all.

      • alexsubq 12 days ago

        What do you want in a whitepaper that was not in our blog post? There is time to add more before the whitepaper is released.

        • jazzypants 11 days ago

          I'm not GP, but I would want a benchmark that actually tests the entire context window. A benchmark that only tests the first 128K tokens effectively tells us nothing about how well it works at its full capacity.

  • jakevoytko 15 days ago

    The proof is in the pudding. At this point, there have been plenty of models that overperformed on benchmarks and underperformed on real work. So my stance is that I'm curious, I'm excited to see where it goes, and I don't believe it until I can try it.

  • dvfjsdhgfv 14 days ago

    > Am I missing something?

    Yes, this product doesn't exist.

    And the last time a company claimed something similar it disappeared after taking money from investors.

  • amw-zero 14 days ago

    Yes you're missing something: the snake oil.

  • shdh 15 days ago

    no one has access to it yet

    no published benchmarks

    no paper

    no demonstrations of capabilities

  • remaximize 15 days ago

    I agree, it's a real architectural breakthrough if true

_burner256 14 days ago

Funny how they claim a 12M context window, yet all benchmarks are cherry picked with a 1M context window. Also, nobody has questioned how they did a training run before receiving funding. SoTA training runs cost well above $10M, yet no mention of funding prior to yesterday, interesting.

creamyhorror 15 days ago

Whether this is real or not, multiple commenters here look like astroturfers - created in the past year (or hours) with very low karma

  • GorbachevyChase 15 days ago

    There are some comments which are identical to comments on X as well. That is not the say the frontier labs do not engage in highly unethical marketing, but this is a little bit too obvious.

in-silico 14 days ago

I wonder how different their method actually is from other sub-quadratic sparse attention methods like Reformer [1] and Routing Transformer [2].

[1]: https://arxiv.org/abs/2001.04451

[2]: https://arxiv.org/abs/2003.05997

remaximize 15 days ago

This is pretty remarkable. We've spent a lot of time finding workarounds for LLMs reading long docs. Now that's gone.

roflcopter69 9 days ago

I'm usually okay with most LLM-assisted writing, but the amount of "it's not X. it's Y" style of phrases in https://subq.ai/how-ssa-makes-long-context-practical is disturbing.

Also, holy moly, the astroturfing.

But I'll still keep an eye on what they'll show up with in the next months. Sounds intriguing.

charliecs 9 days ago

Don't let a C-suite marketing video blow your mind. They are trying to discover the new Transformer, that's not easy. 12 million token context with worse quality means this isn't going anywhere. Want to bet me bitcoin that we won't be talking about them in 1 year? Heck, they may have found something great, but the prior should be one of skepticism.

kovek 14 days ago

> The core idea is content-dependent selection. For each query, the model selects which parts of the sequence are worth attending to, and computes attention exactly over those positions.

I don't know if this will help for things like understanding code, where the all relevant parts can be the file of 1000 lines that we are analyzing, and where every token is relevant in understanding recursion, loops, function calls, etc.

This sounds like it would be great to do SSA before passing things along to a code model like claude code.

Let me know if I misunderstood

  • alexsubq 12 days ago

    Yeah, tokens are excluded, only pairwise relationships between tokens. Coding is something we are looking at carefully!

williamimoh 15 days ago

Looks like long context isn’t a problem anymore

  • tamarru 15 days ago

    Neither is cost, and latency, in the long-term. LLMs ultimately become more economically viable than they are now, and broaden the scope of every existing LLM-driven application (particularly STS, conversational AI, etc, etc.)

lostmsu 11 days ago

No API access for independent verification - vaporware. See also comment about astroturfing accounts in this thread.

noashavit 11 days ago

An architecture where compute grows linearly with context length seems dangerous. It can get very expensive as context grows and performance degrades

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection