[HN Gopher] Zebra-Llama - Towards efficient hybrid models
       ___________________________________________________________________
        
       Zebra-Llama - Towards efficient hybrid models
        
       Author : mirrir
       Score  : 107 points
       Date   : 2025-12-06 20:15 UTC (1 days ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | mason_mpls wrote:
       | > Zebra-Llama achieves Transformer-level accuracy with near-SSM
       | efficiency using only 7-11B training tokens (compared to
       | trillions of tokens required for pre-training) and an 8B teacher.
       | Moreover, Zebra-Llama dramatically reduces KV cache size--down to
       | 3.9%, 2%, and 2.73% of the original for the 1B, 3B, and 8B
       | variants, respectively--while preserving 100%, 100%, and 97% of
       | average zero-shot performance on LM Harness tasks.
       | 
       | This is an extraordinary claim, is there a catch I'm missing? Am
       | I misreading?
        
         | jychang wrote:
         | The catch that you're missing is that Deepseek did this ages
         | ago.
         | 
         | They're just using MLA, which is well known to reduce KV size
         | by 90%. You know, the MLA that's used in... Deepseek V2,
         | Deepseek V3, Deepseek R1, Deepseek V3.1, Deepseek V3.2.
         | 
         | Oh, and they also added some hybrid linear attention stuff to
         | make it faster at long context. You know who else uses hybrid
         | linear attention? Deepseek V3.2.
        
           | erichocean wrote:
           | Kimi K2 also uses MLA, and Kimi Linear runs Kimi Delta
           | Attention (it's SSM-like) for three out of every four layers
           | (the fourth uses MLA).
        
             | jychang wrote:
             | Kimi K2 is literally a "copy Deepseek's homework" model.
             | Seriously. It's even exactly 61 layers, the same as
             | Deepseek V3/R1.
        
               | logicprog wrote:
               | For a "copy Deepseek's homework" model, it's really good,
               | preferable to DeepSeek for me (at least prior to V3.2,
               | which I haven't been able to fully put through its paces
               | yet). post-training really makes that much of a
               | difference I guess
        
           | storus wrote:
           | Linear attention is really bad, it's only good for
           | benchmaxing but it leads to a loss of valuable granularity,
           | which can be felt in the latest DeepSeek randomly
           | forgetting/ignoring/correcting explicitly stated facts in the
           | prompt.
        
       | adityashankar wrote:
       | Due to perverse incentives and the historical nature of models
       | over-claiming accuracy, it's very hard to believe anything until
       | it is open source and can be tested out
       | 
       | that being said, I do very much believe that computational
       | efficiency of models is going to go up [correction] drastically
       | over the coming months, which does pose interesting questions
       | over nvidia's throne
       | 
       | *previously miswrote and said computational efficiency will go
       | down
        
         | danielbln wrote:
         | I think you mean computational efficiency will go _up_ in the
         | future. To your last point: Jevons paradox might apply.
        
           | adityashankar wrote:
           | yup that's what I meant!, Jevon's paradox applies to resource
           | usage in general and not towards a specific companies
           | dominance
           | 
           | if computational efficiency goes up (thanks for the
           | correction), and CPU inference becomes viable for most
           | practical applications, GPUs (or accelerators) themselves may
           | be unnecessary for most practical functions
        
             | atq2119 wrote:
             | Discrete GPUs still have an advantage in memory bandwidth.
             | Though this might push platforms like laptops towards
             | higher bandwidths, which would be nice.
        
         | credit_guy wrote:
         | Like this?
         | 
         | https://huggingface.co/amd/Zebra-Llama-8B-8MLA-24Mamba-SFT
        
           | adityashankar wrote:
           | yes!, thanks for the link!
        
           | moffkalast wrote:
           | GGUF when? /s
        
           | deepdarkforest wrote:
           | > which does pose interesting questions over nvidia's
           | throne...
           | 
           | > Zebra-Llama is a family of hybrid large language models
           | (LLMs) proposed by AMD that...
           | 
           | Hmmm
        
           | jychang wrote:
           | Or like this: https://api-docs.deepseek.com/news/news251201
           | 
           | I don't know what's so special about this paper.
           | 
           | - They claim to use MLA to reduce KV cache by 90%. Yeah,
           | Deepseek invented that for Deepseek V2 (and also V3 and
           | Deepseek R1 etc)
           | 
           | - They claim to use a hybrid linear attention architecture.
           | So does Deepseek V3.2 and that was weeks ago. Or Granite 4,
           | if you want to go even further back. Or Kimi Linear. Or
           | Qwen3-Next.
           | 
           | - They claimed to save a lot of money not doing a full pre-
           | train run for millions of dollars. Well, so did Deepseek
           | V3.2... Deepseek hasn't done a full $5.6mil full pretraining
           | run since Deepseek V3 in 2024. Deepseek R1 is just a $294k
           | post train on top of the expensive V3 pretrain run. Deepseek
           | V3.2 is just a hybrid linear attention post-train run - i
           | don't know the exact price, but it's probably just a few
           | hundred thousand dollars as well.
           | 
           | Hell, GPT-5, o3, o4-mini, and gpt-4o are all post-trains on
           | top of the same expensive pre-train run for gpt-4o in 2024.
           | That's why they all have the same information cutoff date.
           | 
           | I don't really see anything new or interesting in this paper
           | that isn't already something Deepseek V3.2 has already sort
           | of done (just on a bigger scale). Not exactly the same, but
           | is there anything amazingly new that's not in Deepseek V3.2?
        
             | T-A wrote:
             | From your link: DeepSeek-V3.2 Release 2025/12/01
             | 
             | From Zebra-Llama's arXiv page: Submitted on 22 May 2025
        
               | jychang wrote:
               | That's still behind the times. Even the ancient dinosaur
               | IBM had released a Mamba model [1] before this paper was
               | even put out.
               | 
               | > Granite-4.0-Tiny-Base-Preview is a 7B-parameter hybrid
               | mixture-of-experts (MoE) language model featuring a 128k
               | token context window. The architecture leverages Mamba-2,
               | superimposed with a softmax attention for enhanced
               | expressiveness, with no positional encoding for better
               | length generalization. Release Date: May 2nd, 2025
               | 
               | I mean, good for them for shipping, I guess. But
               | seriously, I expect any postgrad student to be able to
               | train a similar model with some rented GPUs. They
               | literally teach MLA to undergrads in the basic LLM class
               | at Stanford [2] so this isn't some exactly some obscure
               | never-heard-of concept.
               | 
               | [1] https://huggingface.co/ibm-granite/granite-4.0-tiny-
               | base-pre...
               | 
               | [2] https://youtu.be/Q5baLehv5So?t=6075
        
               | Palmik wrote:
               | DeepSeek's MLA paper was published in 2024:
               | https://arxiv.org/abs/2405.04434
               | 
               | DeepSeek's Sparse Attention paper was published in
               | February: https://arxiv.org/abs/2502.11089
               | 
               | DeepSeek 3.2 Exp (combining MLA and DSA) was released in
               | September.
               | 
               | You also had several other Chinese hybrid models, like
               | Qwen3 Next and Minimax M1.
        
             | nickpsecurity wrote:
             | "Deepseek hasn't done a full $5.6mil full "
             | 
             | Don't forget the billion dollars or so of GPU's they had
             | access to that they left out of that accounting. Also, the
             | R&D cost of the Meta model they originally used. Then, they
             | added $5.6 million on top of that.
        
             | credit_guy wrote:
             | Here's what's important about this paper. It is written by
             | AMD researchers. It shows AMD is investing in AI research.
             | Is this the same level of achievement as DeepSeek 3.2. Most
             | likely not. Do they have novel ideas? Difficult to say,
             | there are hundreds of new ideas being tried in this space.
             | Is this worthless? Most certainly not. In order to make
             | progress in this domain (as in any other), you first need
             | to get your feet wet. You need to play with the various
             | components, and see how they fit together. The idea in this
             | paper is that you can combine somehow SSMs (like Mamba) and
             | LLMs (like LLama). The examples they give are absolute toys
             | compared to DeepSeek 3.2 (the largest is 8 billion
             | parameters, while DeepSeek 3.2 has 671 billion parameters).
             | The comparison you are trying to make simply does not
             | apply. The good news for all of us is that AMD is working
             | in this space.
        
               | jychang wrote:
               | Mamba based LLMs aren't even close to novel though. IBM's
               | been doing this since forever [1].
               | 
               | Also, you're off on Deepseek V3.2's param count, the full
               | model's 685B in size with the MTP layer.
               | 
               | I don't think there's anything interesting here other
               | than "I guess AMD put out a research paper", and it's not
               | cutting edge when Deepseek or even IBM is running laps
               | around them.
               | 
               | [1] Here's a news article from April, although IBM has
               | been doing it for a long time before that
               | https://research.ibm.com/blog/bamba-ssm-transformer-model
        
             | SilverElfin wrote:
             | How did you get all this info about how each is trained? Is
             | that something they admit now or is it through leaks?
        
               | jychang wrote:
               | Deepseek? It's literally in their research papers.
               | 
               | OpenAI? The OpenAI head of research @markchen90 straight
               | up admitted it in a podcast.
               | 
               | https://x.com/petergostev/status/1995744289079656834
               | 
               | "In the last 2 years we've put so much resourcing into,
               | into reasoning and one byproduct of that is you lose a
               | little bit of muscle on pre training and post training."
               | "In the last six months, @merettm and I have done a lot
               | of work to build that muscle back up." "With all the
               | focus on RL, there's an alpha for us because we think
               | there's so much room left in pre training." "As a result
               | of these efforts, we've been training much stronger
               | models. And that also gives us a lot of confidence
               | carrying into Gemini 3 and other releases coming this end
               | of the year."
               | 
               | Note, "alpha" in the quote above is referring to
               | https://en.wikipedia.org/wiki/Alpha_(finance)
               | 
               | But it's pretty clear that the last full pretrain run
               | they've released is for gpt-4o 2 years ago*, and since
               | then they've just been iterating RL for their models. You
               | don't need any insider information to notice that, it's
               | pretty obvious.
               | 
               | *Excluding GPT-4.5 of course, but even OpenAI probably
               | wants us to forget about that.
        
               | nl wrote:
               | Semi-analysis also believes they haven't done a fill
               | pretraining run since 4o (except for GPT-4.5): https://op
               | en.substack.com/pub/semianalysis/p/tpuv7-google-ta...
        
             | twotwotwo wrote:
             | These are potentially complementary approaches. Various
             | innovations have shrunk the KV cache size or (with DSA) how
             | much work you have to do in each attention step. This paper
             | is about hybrid models where some layers' state needs don't
             | grow with context size at all.
             | 
             | SSMs have a fixed-size state space, so on their own they'll
             | never going be able to recite a whole file of your code in
             | a code-editing session for example. But if much of what an
             | LLM is doing _isn 't_ long-distance recall, you might be
             | able to get away with only giving some layers full recall
             | capability, with other layers manipulating the info already
             | retrieved (plus whatever's in their own more limited
             | memory).
             | 
             | I think Kimi Linear Attention and Qwen3-next are both doing
             | things a little like this: most layers' attention/memory
             | doesn't grow with context size. Another approach, used in
             | Google's small open Gemma models, is to give some layers
             | only 'local' attention (most recent N tokens) and give a
             | few 'full' (whole context window) attention. I guess we're
             | seeing how those approaches play out and how different
             | tricks can be cobbled together.
             | 
             | There can potentially be a moneyball aspect to good model
             | architecture. Even if _on its own_ using space-saving
             | attention mechanisms in some layers of big models cost
             | something in performance, their efficiency could allow you
             | to  'spend' more elsewhere (more layers or more params or
             | such) to end with overall better performance at a certain
             | level of resources. Seems like it's good to have
             | experiments with many different approaches going on.
        
         | ACCount37 wrote:
         | I don't doubt the increase in efficiency. I doubt the
         | "drastically".
         | 
         | We already see models become more and more capable per weight
         | and per unit of compute. I don't expect a state-change
         | breakthrough. I expect: more of the same. A SOTA 30B model from
         | 2026 is going to be ~30% better than one from 2025.
         | 
         | Now, expecting that to hurt Nvidia? Delusional.
         | 
         | No one is going to stop and say "oh wow, we got more inference
         | efficiency - now we're going to use less compute". A lot of
         | people are going to say "now we can use larger and more
         | powerful models for the same price" or "with cheaper inference
         | for the same quality, we can afford to use more inference".
        
           | colechristensen wrote:
           | Eh.
           | 
           | Right now, Claude is good enough. If LLM development hit a
           | magical wall and never got any better, Claude is good enough
           | to be terrifically useful and there's diminishing returns on
           | how much good we get out of it being at $benchmark.
           | 
           | Saying we're satisfied with that... well how many years until
           | efficiency gains from one side and consumer hardware from the
           | other meet in the middle so "good enough for everybody" open
           | models are available for anyone who wants to pay for a $4000
           | MacBook (and after another couple of years a $1000 MacBook,
           | and several more and a fancy wristwatch).
           | 
           | Point being, unless we get to a point where we start
           | developing "models" that deserve civil rights and
           | citizenship, the years are numbered to where we NEED cloud
           | infrastructure and datacenters full of racks and racks of
           | $x0,000 hardware.
           | 
           | I strongly believe the top end of the S curve is nigh, and
           | with it we're going to see these trillion dollar ambitions
           | crumble. Everybody is going to want a big-ass GPU and a ton
           | of RAM but that's going to quickly become boring because open
           | models are going to exist that eat everybody's lunch and the
           | trillion dollar companies trying to beat them with a premium
           | product aren't going to stack up outside of niche cases and
           | much more ordinary cloud compute motivations.
        
             | ACCount37 wrote:
             | Good enough? There's no such thing.
             | 
             | People said that "good enough" about GPT-4. Now you say
             | that about Claude Opus 4.5. How long before the treadmill
             | turns, and the very same Opus 4.5 becomes "the bare
             | minimum" - the least capable AI you would actually consider
             | using for simple and unimportant tasks?
             | 
             | We have miles and miles of AI advancements ahead of us. The
             | end of that road isn't "good enough". It's "too powerful to
             | be survivable".
        
               | cyanydeez wrote:
               | Elon will boil the oceans if it means not having to deal
               | with poor people.
        
               | colechristensen wrote:
               | I can build fully functional applications without writing
               | a single line of code with Claude. In my free time. On a
               | weekend. I'm going to release one of them pretty soon. A
               | toddler being able to do this instead of an industry
               | veteran isn't that compelling. Avoiding the few pitfalls
               | of the LLM getting stuck and taking a while to get out
               | isn't that valuable.
               | 
               | >Good enough? There's no such thing.
               | 
               | This is just wrong. Maybe you can't imagine good enough,
               | I can. And I think "better" is going to start getting
               | diminishing returns as the velocity of improvements I
               | expect to slow and the _value_ of improvements are going
               | to become less meaningful. The  "cost" of a LLM making
               | mistakes is already pretty low, cutting it in half is
               | better, sure, but it's so low already I don't
               | particularly care if it gets some multiple more rare.
        
               | grogers wrote:
               | LLM only fairly recently underwent a step change from
               | "maybe someday" to actually useful now. That opened many
               | new doors that people didn't even think were possible.
               | Getting incrementally better at something they are
               | already pretty good at isn't that impressive. But getting
               | drastically better at something they are currently bad
               | at, _will_ drive new models and new research.
        
             | buu700 wrote:
             | Coding capability in and of itself may be "good enough" or
             | close to it, but there's a long way to go before AI can
             | build and operate a product end-to-end. In fairness, a lot
             | of the gap may be tooling.
             | 
             | But the end state in my mind is telling an AI "build me
             | XYZ", having it ask all the important questions over the
             | course of a 30-minute chat while making reasonable
             | decisions on all lower-level issues, then waking up the
             | next morning to a live cloud-hosted test environment at a
             | subdomain of the domain it said it would buy along with
             | test builds of native apps for Android, iOS, Linux, macOS,
             | and Windows, all with near-100% automated test coverage and
             | passing tests. Coding agents feel like magic, but we're
             | clearly not there yet.
             | 
             | And that's just coding. If someone wanted to generate a
             | high-quality custom feature-length movie within the usage
             | limits of a $20/mo AI plan, they'd be sorely disappointed.
        
               | colechristensen wrote:
               | >But the end state in my mind is telling an AI "build me
               | XYZ", having it ask all the important questions over the
               | course of a 30-minute chat while making reasonable
               | decisions on all lower-level issues, then waking up the
               | next morning to a live cloud-hosted test environment at a
               | subdomain of the domain it said it would buy along with
               | test builds of native apps for Android, iOS, Linux,
               | macOS, and Windows, all with near-100% automated test
               | coverage and passing tests. Coding agents feel like
               | magic, but we're clearly not there yet.
               | 
               | I'm pretty sure we're there. I'm not sure how interested
               | I am in completely closing that loop and completely
               | removing the human from the loop. But I'm also pretty
               | confident that I could do it with nothing but existing
               | models and software built around them.
        
               | buu700 wrote:
               | I'm not aware that we are there, but would be very
               | interested if you have information to the contrary. Even
               | if we were there, the product/service that does it would
               | have to be at a reasonable cost in order to be useful for
               | most people.
               | 
               | As I said, a lot of the gap may be tooling. But I'm
               | skeptical that even the models themselves are capable of
               | that given sufficiently advanced tooling. I'm not saying
               | we're not _close_ (certainly much closer than we were at
               | the start of the decade), but if we were actually there,
               | you would have zero reservations about removing the human
               | from the loop of an initial prototype.
        
               | colechristensen wrote:
               | My information to the contrary is my experience in the
               | last few weeks building things with LLMs including
               | tooling to help build things with LLMs. The is experience
               | is one of ... I'm a product manager and devsecops
               | engineer bullying an LLM with the psychology of a toddler
               | into building great software which it _can_ do very
               | successfully. A single instance of a model with a single
               | rolling context window and one set of prompts absolutely
               | can 't do what you want, but that's not what I've been
               | doing.
               | 
               | Oneshotting applications isn't interesting to me because
               | I _do_ want to be involved, there are things I have
               | opinions about that I won 't _know_ I will have until we
               | get there and there are definitely times where I want to
               | pivot a little or a lot in the middle of development
               | based on experience, an actually agile development cycle.
               | 
               | In the same way I wouldn't want to hire a wedding planner
               | or house builder to plan my wedding or build my home
               | based entirely on a single short meeting before anything
               | started, I don't want to one shot software.
               | 
               | There _are_ all sorts of things where I want to get
               | myself out of the loop because they 're stupid problems,
               | some of them I've fixed, others I'd rather fix later
               | because doing the thing is more interesting than pausing
               | and building the tools to make the thing.
               | 
               | There is I think an inverse relationship between the
               | complexity of the tooling and the amount of human
               | involvement; for me I've reached or am quite near the
               | amount of human involvement where I'm much more excited
               | about building stuff than saving more of my attention.
               | 
               | I'm being a bit vague because I'm not sure I want to
               | share all of my secrets just yet.
        
               | buu700 wrote:
               | Just to be clear, what I was proposing was a single tool
               | which would, on the basis of a single ~30-minute
               | interaction, purchase a domain name, set up a cloud
               | environment, build a full-stack application + cross-
               | platform native apps + useful tests with near-100%
               | coverage, deploy a live test environment, and compile
               | each platform's native app -- all entirely autonomously.
               | Are you saying you've used or built something similar to
               | that? That is super interesting if so, even if you're
               | unable to share. A major subset of that could also still
               | be incredibly useful, but the whole solution I described
               | is a very high bar.
               | 
               | I've been very successful building with custom LLM
               | workflows and automation myself, but that's beyond the
               | capabilities of any tooling I've seen, and I wouldn't
               | necessarily expect great results with current models even
               | if current tooling were fully capable of what I
               | described. Even with such tooling, the cost of inference
               | is high enough to deter careless usage without much more
               | rigorous work on the initial spec and/or micromanagement
               | of the development process.
               | 
               | I'm not necessarily _advocating_ for one-shotting in any
               | given context. I 'm simply pointing out that there would
               | be huge advantages to LLMs and tooling sufficiently
               | advanced to be fully capable of doing so end-to-end,
               | especially at dramatically lower cost than current models
               | and at superhuman quality. Such an AI could conceivably
               | one-shot any possible project idea, in the same sense
               | that a competent human dev team with nothing but a page
               | of vague requirements and unlimited time could at least
               | eventually produce _something_ functional.
               | 
               | The value of such an AI is that we'd use it in ways that
               | sound ridiculous today. Maybe a chat with some guy at a
               | bar randomly inspires a neat idea, so you quickly whip
               | out your phone and fire off some bullet point notes; by
               | the time you get home, you have 10 different near-
               | production-ready variations to choose from, each with
               | documentation on the various decisions its agent made and
               | why, and each one only cost $5 in account credit. None is
               | quite perfect, but through the process you've learned a
               | lot and substantially refined the idea; you give it a
               | second round of notes and wake up to a new testable
               | batch. One of those has the functional requirements just
               | right, so you make the final decisions on non-functional
               | requirements and let it roll one last time with strict
               | attention to detail on code quality and a bunch of cycles
               | thrown at security review.
               | 
               | That evening, you check back in and find a high-quality
               | final implementation that meets all of your requirements
               | with a performant and scalable architecture, with all
               | infrastructure deployed and apps submitted to all
               | stores/repositories. You subsequently allocate a sales
               | and marketing budget to the AI, and eventually notice
               | that you suddenly have a new source of income. Now
               | imagine that instead of you, this was actually your
               | friend who's never written a line of code and barely
               | knows how to use a computer.
               | 
               | I still agree with you that current models have been
               | "good enough" for some time, in the sense that if LLMs
               | froze today we could spend the next decade collectively
               | building on and with them and it would totally transform
               | the economy. But at the same time, there's definitely
               | latent demand for more and/or better inference. If LLMs
               | were to become radically more efficient, we wouldn't
               | start shuttering data centers; the economy would just
               | become that much more productive.
        
               | nl wrote:
               | Have you tried Loveable, Replit, V0 etc?
               | 
               | Outside of purchasing the domain and native apps for you
               | they cover a very significant amount of this.
               | 
               | If you insist on Native Apps, it's possible Google Jules
               | could do it. With Gemini 2.5 it wasn't strong enough but
               | I think it has Gemini 3 now which can definitely do
               | native apps just fine.
        
               | buu700 wrote:
               | Thanks for the recommendations. Regarding your other
               | comment, Flutter is what I've landed on as well for my
               | next cross-platform app project, and I'm currently in the
               | middle of developing a spec for a fairly complex agentic
               | system that I'm going to try having Codex two-shot (basic
               | project setup + file stubs + exhaustive tests -> manual
               | checkpoint -> TDD the rest).
               | 
               | I haven't tried Lovable, V0, or Jules, but I really like
               | Replit for certain things. Having said that, based on my
               | experience, I would characterize it as an amazing tool
               | for rapid frontend iteration with prototype-level backend
               | creation. I'm sure it's gotten better at one-shotting
               | since I tried Agent 2 with Sonnet 3.7 in May, but would
               | still be very (pleasantly) surprised to see that Agent 3
               | with current models could meet the incredibly high bar of
               | wholly replacing a human dev team.
               | 
               | The fact that tools like Replit also include their own
               | hosting environments is definitely neat, but not really
               | what I was getting at as far as deployment. What I had in
               | mind was managing arbitrary cloud platforms, setting up
               | an optimal architecture for your anticipated scale and
               | usage patterns -- whether that's a single Hetzner
               | instance with SQLite or horizontally scaled app servers
               | behind an API gateway with Kafka, Valkey, and Spanner or
               | ScyllaDB -- and doing all the DevOps to handle that along
               | with things like CI/CD.
               | 
               | I'm not downplaying how amazing these capabilities are.
               | Being able to generate high-quality code from natural
               | language feels like magic. But all the parts beyond
               | narrow application code are half of the thing I
               | described:
               | 
               | * I'm saying you should be able to send a single off-the-
               | cuff drunk text to an AI and later find a complete
               | production-ready SaaS startup that fully aligns with a
               | reasonable interpretation of your message.
               | 
               | * The other half of the whole thing is >=human-level
               | execution. If the AI can't autonomously deliver work
               | comparable to what an experienced CTO would (given the
               | same requirements, an arbitrarily large hiring budget,
               | and a stipulation to never contact you again until the
               | work was done), it's not there yet.
               | 
               | Again, none of this is to dunk on agentic coding. My
               | point is that I set an absurdly high bar because I want
               | it to one day be met. Just as a $100 storage budget today
               | is equivalent to $100m a few decades ago, I want to live
               | to see a $100 engineering budget reach equivalency with
               | last decade's $100m.
        
               | sureglymop wrote:
               | Given that natural language is ambiguous, what if the LLM
               | makes some mistakes though?
               | 
               | I'm wondering because, it's not like it's a human that
               | can then take accountability/responsibility for that...
        
               | nl wrote:
               | > But the end state in my mind is telling an AI "build me
               | XYZ", having it ask all the important questions over the
               | course of a 30-minute chat while making reasonable
               | decisions on all lower-level issues, then waking up the
               | next morning to a live cloud-hosted test environment at a
               | subdomain of the domain it said it would buy along with
               | test builds of native apps for Android, iOS, Linux,
               | macOS, and Windows, all with near-100% automated test
               | coverage and passing tests. Coding agents feel like
               | magic, but we're clearly not there yet.
               | 
               | If you take out the native builds we are there now. V0,
               | Lovable, etc really do a great job of this. If you want
               | an IDE-like environment Antigravity is pretty good too.
               | 
               | The native builds thing is completely doable too. I've
               | built cross platform apps in 30 minutes of my time using
               | Codex+Flutter. It really does work.
        
       | Reubend wrote:
       | It would be REALLY cool to see this same technique applied to a
       | much more recent OSS model distillation. For example, Mistral 3
       | 14B would be a great target. How efficient can we get inference
       | there?
        
       | a_wild_dandan wrote:
       | If the claims in the abstract are true, then this is legitimately
       | revolutionary. I don't believe it. There are probably some major
       | constraints/caveats that keep these results from generalizing.
       | I'll read through the paper carefully this time instead of a skim
       | and come back with thoughts after I've digested it.
        
         | jychang wrote:
         | What's not to believe? Qwerky-32b has already done something
         | similar as a finetune of QwQ-32b but not using traditional
         | attention architecture.
         | 
         | And hybrid models aren't new, MLA based hybrid models is
         | basically just Deepseek V3.2 in a nutshell. Note that Deepseek
         | V3.2 (and V3.1, R1, and V3... and V2 actually) all use MLA.
         | Deepseek V3.2 is what adds the linear attention stuff.
         | 
         | Actually, since Deepseek V3.1 and Deepseek V3.2 are just post-
         | training on top of the original Deepseek V3 pretrain run, I'd
         | say this paper is basically doing _exactly_ what Deepseek V3.2
         | did in terms of efficiency.
        
           | cubefox wrote:
           | DeepSeek-V3.2 is a sparse attention architecture, while
           | Zebra-Llama is a hybrid attention/SSM architecture. The
           | outcome might be similar in some ways (close to linear
           | complexity) but I think they are otherwise quite different.
        
       | xer wrote:
       | This is great! But what if the US invests 1% of GDP in GPU
       | datacenters and then those are not needed becaues someone created
       | a much more efficient architecture?
        
         | _boffin_ wrote:
         | They will still use capacity. Why would you believe anything
         | different?
        
         | wild_egg wrote:
         | More efficiency just means more consumption. Think when they
         | add lanes to a highway, traffic gets better for a little bit
         | but very soon the highway is just as congested as before.
        
           | wilg wrote:
           | More people get where they're going in the same amount of
           | time though
        
         | dkural wrote:
         | Look up Jevons Paradox, when something becomes more efficient,
         | consumption can goes up, often due to price elasticity.
         | 
         | Think of like this: Imagine car prices go from $200,000 to
         | $$20,000 - you wouldn't sell 10x the amount of cars, you'd sell
         | --- In fact I just looked up the numbers - worldwide only 100K
         | or so cars are 200K & higher, whereas roughly 80 million cars
         | are in that affordable category.
         | 
         | So a price drop of 90% allowed sales to go from 0.1M to 80M!! I
         | think this means we need more engines, tires, roads, gas, spare
         | parts.
        
         | chpatrick wrote:
         | Then they'll be able to use those datacenters much more
         | efficiently.
        
       | AlexCoventry wrote:
       | This is from May 2025, according to the arxiv watermark. Maybe
       | that should be mentioned in the title.
        
       | KnuthIsGod wrote:
       | Looks like the trillions of dollars spent on datacentres will end
       | up being regretted.
        
         | pryelluw wrote:
         | I should have been an electrician.
        
       ___________________________________________________________________
       (page generated 2025-12-07 23:02 UTC)