Settings

Theme

DaisyRose-27B

radixark.com

223 points by de_sty · 86 comments

Reader

12 threads
chriddyp

Very excited to see more post-training happening on these open models. Looking forward to trying this one out once it makes its way onto OpenRouter.

Qwen 27B really punches above its weight. 27B is small enough to fit on a Mac Mini / Macbook Pro which is very exciting.

Starting to see more promising examples of companies post-training. From my evals [1], I've tested 3 so far:

1. Fireworks' Ember-1 (postrained on Kimi K3, improved score by 10% in my evals)

2. Particle AI's Particle-1 (fine-tuned on DeepSeek V4.1 Flash, also a 10% improvement and a bit cheaper and faster)

3. Nex AGI's Nex-N2.6 (post-trained on GLM 5.3 Flash. Didn't show an improvement in my eval, and had a couple runaway loops that made it expensive).

With Thinking Machines' western open model release (Inkling Small) a few weeks ago, I expect we'll see more of this, especially out of western companies.

[1] https://plotly.com/blog/nex-n2-6-plotly-data-analytics-bench...

woah

The heavy reliance on eval datasets showcased here and also evidenced by the frontier lab's high payments for such data cast doubt on the claims that AI will become self-improving soon

  • anon373839

    The frontier labs want you to believe that their models are magically gaining intelligence that generalizes to new areas with each new release. But it’s an illusion: the models are post-trained on a HUGE array of hand-curated datasets for specific tasks, with good enough coverage that it feels general.

    • harry8

      The frontier labs are using all their customers' logs to train. It's the best training set there is.

      • XenophileJKO

        I don't think your data is as valuable as you think it is.

        I would not want a model trained on user conversations.

        • visarga

          It is longitudinal data with LLM responses to human tasks and outcomes showing up later in the stream, you can use hindsight to see how a LLM response fared, humans come back and bring those outcomes to continue iterating.

        • Bnjoroge

          it's pretty valuable, and there's a huge demand for it from data labs depending on the kind of data. Agent traces are also pretty valuable

        • MisterMunchkin

          So you’re telling me you haven’t uploaded any internal company documents or discussed any of your company projects?

          Why do you think they’re getting into consulting, right after ingesting everyone’s statements of work?

      • jhancock

        Both OpenAI and Anthropic have setting that allow (at least paid customers) to ensure their data is not used for training. Do you have reason to believe this setting is not what most user believe it is?

        • endgame

          Anthropic used to charge you API rates if it saw a HERMES.md in the repo you were working on, even if you had a subscription: https://github.com/anthropics/claude-code/issues/53262

          Another commenter here: https://news.ycombinator.com/item?id=49502774

          > I made it to a third round interview at anthropic in 2024 and they had me build a web crawler as their programming test. Part way through I started on making it respect robots.txt and I could immediately tell they were no longer interested in me.

          Everything but the core models seems to be some mixture of slapdash, petty, and reckless. I would absolutely believe they'd train on customer conversations. Where else would those customers go?

        • anon373839

          I think if you read the legal agreements adversarially, there are a lot of cracks in them the labs can exploit. For example, what about derivative data such as LLM-generated summaries of your sessions? Do the training settings preclude use of that?

        • ipaddr

          Both tell you not to include password/tokens in chat. Why would it matter if they weren't training

          • olejorgenb

            Because the session transcripts are stored on disk (and optionally in cloud). And if they end up in the chat they could end up as input to other services.

          • ben_w

            I'm not saying to trust the companies here, but there are other reasons to make sure people don't do that.

            AI are now tool users. If you give ChatGPT your password, you should expect that instance of ChatGPT to use it. Given the current state of affairs, HuggingFace etc., this will likely go badly wrong and break something.

            And of course we don't want vibe coded software written by someone who gives their LLM a hard coded password because they don't know any better.

          • d-lowl

            You don't want your password to be used as an input to some tool call do you?

        • harry8

          Seriously who the f@&k actually believes that? The mind boggles that people actually say “there’s a setting.” Is it next to the one that says they won’t break the law and infringe copyright to train their models?

          Sam Altman, would you actually believe anything he said if he had an incentive to lie to you?

          Rieman hypothesis story was not secret. How do you even entertain this stuff for a second? Even if it were in your financial interest to not understand it’s just so very stark.

          The AI companies will tell whatever lie helps them and won’t blink when caught and there will be no consequences because we’ve seen it. Repeatedly. There isn’t a grey area…

        • duskdozer

          Even if you believe they honor it, which you shouldn't, all they have to do it make an update and change the setting to a new opt-out version, and then -poof- you've "consented" just long enough for them to feed your entire account history in. I mean how many times do companies have to do these things until people learn?

      • jpardoe

        That depends on the customer. How can you detect the ones that are making smart decisions and guiding the agent correctly towards better outcomes? If you could know that then the problem would already be solved.

      • boardendgrain

        Time to do all business in cockney ryming slang!

        • techcode

          All the hours that went into watching "Only Fools And Horses" will finally pay off.

    • BobbyTables2

      I’ve been suspecting that as a stochastic parrot cannot reason…

      Early LLMs couldn’t answer how many R’s in strawberry. Now they can… Perhaps they just recognize the question and know which “helper” to use?

      However, I find Claude Opus connects the dots in large codebases in ways that aren’t simple parlour tricks…

      But who knows, maybe our own reasoning isn’t all that we think it is. Our ability to spell words isn’t too different - many patterns fuzzily drilled into the head until we can spell most things…

    • Taek

      Me and a couple of other top engineers have noticed that the latest round of models (everything after Gemini 3.0, GPT 5.6, Fable 5.0) seems to be less intelligent and less capable of solving unusual tasks. For example, Gemini 4 is a major regression vs 3 on being able to transcribe my girlfriend (who has a very thick, rapid, coastal Colombian Spanish dialect).

      They are getting much better at the common case. But it feels like we're moving away from AGI and RSI as a tradeoff.

      • ben_w

        > They are getting much better at the common case. But it feels like we're moving away from AGI and RSI as a tradeoff.

        We can but hope.

        On the flip side, being good at just maths may solve whatever difference it is that makes all biological brains learn from fewer examples than all machine learning.

    • 0xWTF

      How is that different from you?

      • StilesCrisis

        Humans generalize much more quickly than models? We don't require millions of curated examples to learn a concept?

        • p-e-w

          Because there is four billion years of evolutionary pre-training.

          • ben_w

            Cars didn't exist 150 years ago, yet we do not need the trillion miles of experience that it took Tesla to reach merely a small geofenced region where a steering wheel is not needed; how much would a human need for the same? A thousand miles as a learner? A hundred?

            Ten thousand generations of fire and our jaws still have not fully adapted to cooked food, and yet our minds can learn to cope with it just fine; just one demonstration of why not to pour water on boiling oil can be sufficient.

            And our genome has to cover our whole body, cell metabolism upwards, not specifically our brains.

            There is some stuff our genome gives us, our minds, but it cannot be much. There isn't room for much in our DNA.

          • bavell

            Instead of pre-training, I'd say it's more like a better architecture, training regime, higher fidelity data, and perhaps better initial "weights".

          • octoberfranklin

            In ~8G weights of DNA?

            Lol. That's less than 1 milliFable at 1-bit quantization.

            • jodrellblank

              Maybe not just DNA. "Something needs to speed evolution up" - Denis Noble, Professor of Biology argues against the idea that DNA is instructions and everything else in the body passively takes orders and has no input and no feedback - https://www.youtube.com/watch?v=NAPhBt8VJCM

              • ben_w

                > argues against the idea that DNA is instructions and everything else in the body passively takes orders and has no input and no feedback

                There is feedback between body and DNA; it's at every level from how a foetus gets head and feet in the right place to how it repairs injuries as an adult to how exercise triggers muscle growth.

                That isn't doesn't mean there's storgage beyond DNA. There might be some signal molecules which also survive going via sperm and eggs, but they also can't carry much data, and they'd be read by mechanisms generated by the DNA.

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

  • its_down_again

    Curious, where did you see the numbers on how much frontier labs are paying for eval data?

  • charcircuit

    >doubt on the claims that AI will become self-improving soon

    It already happened. https://github.com/karpathy/autoresearch

pkoiralap

Sabi-noema also looks like a close competitor in the same space. Built from qwen3.8 and made better.

https://huggingface.co/sabicap/sabi-noema

Also HF model here: https://huggingface.co/RadixArk/DaisyRose-27B

jacquesm

I always wonder what you lose when you start maxing out some specific benchmark. It is really hard to do this in a balanced way and I would love if everybody that did these kind of efforts would take the time to also list the before/afters of a number of other benchmarks that they did not use in their training.

  • nblintao

    Good point! First of all, none of the benchmark tasks were used in training, though the training data was designed to improve capabilities on tasks like TB4.1. If you consider TB4.1 the main target, the blog actually shows before/after results on several other benchmarks, with no regressions and even some improvements.

    • jacquesm

      Yes, I've seen that, but I wonder what is missing because I find it hard to believe that you can just do some RL and then end up with a model that is better across the board. I would find it far more believable if you outperformed on the benchmark that was your goal (assuming you selected training data to give you an edge there) and underperformed on things that you were not optimizing for. But since it all moves in one direction (better) I feel there must be some kind of unknown at play here. Even so, task specific AI is definitely the future, you don't hire a plumber to do your bookkeeping either...

      • mik1998

        I agree with you and I think, personally, that the heavy post-training like here makes the model more capable in coding but less capable for certain unbenchmarkable tasks, like prose or interpreting prompts correctly. I've been noticing that small models have been gradually being pushed towards programming and are slowly becoming _worse_ at some non-programming tasks, not better; e.g. new Deepseek models appear to be much worse at interpreting metaphors and overall feel more autistic than previous ones.

        • jacquesm

          That mirrors my experience exactly. I keep a couple of older models (and much larger ones as well) for when I want to do stuff that is unrelated to computer programming because the models that are really good at that tend to fare less well at other stuff. I suspect that there is a boundary where maximizing benchmarks for coding at the expense of general knowledge is going to give you a model that is really fast and good but 'narrow' and that this may also lead to loss of performance when applied to coding tasks that are less well represented in the training set (such as, for instance, DSP code). This is a variation on 'the bitter lesson', short term you can make gains like this but long term leveraging compute and data will give you something better. I'm really happy I didn't waste half a life on engineered AI because I would be really quite miserable if I had.

          http://www.incompleteideas.net/IncIdeas/BitterLesson.html

        • techcode

          As electronics/software/systems engineer with brain that's on the spectrum (ADHD, no autism diagnosis ... yet).

          The "Worse at interpreting metaphors and feel more autistic" to me sounds representative of the IT field?

          Obviously - not all of us are on the spectrum. But my (biased) observations suggest that occurance of neurodiversity/spectrum is higher in IT (or more broadly STEM) than in other fields.

          As in - perhaps that (different neuro-wiring, different way of looking at things...etc) is what makes one a better as programming and things of similar nature?

      • reissbaker

        Why do you find it hard to believe that you can do some RL and improve across the board (albeit less strongly on other semi-related tasks than your objective)? That's the idea behind generalization: it's not perfect but you get a little bit of cross-task generalization, so if you just keep spamming more RL environments you can hill-climb to AGI. That's what the labs are doing!

        • jacquesm

          You can hill climb but you will (or at least, I think you will!) lose generality.

          And no, that won't get you to AGI, that is a completely different goal.

          • banghua13

            If you carefully curate the data, plus the original model isn't saturated for RL post-training, it's possible to improve targeted benchmarks without regression on other metrics. This experiment is done with terminal bench 4.1 as a target, and the regression on other benchmarks has been carefully controlled through data + infra design.

            • jacquesm

              Ok, so the obvious question then is: this seems (I'm not saying it is, it just looks like a small thing compared to training up a model from scratch) a relatively trivial undertaking for the authors of the original model, if there was this much left in the tank why didn't they do something similar? Or is there some step here that only this team can perform? Or is it simply a matter of economics?

  • gardnr

    Check the article. It’s the first graphic that has other benchmarks.

xlayn

Snap, no gguf to download, will wait for one to appear to test, any improvement over an already good model is good news.

"18 days on 144 H200 GPUs" insane.. didn't thought so much hardware would be needed to train Qwen.

DeathArrow

One pet project of mine would be - if I had the resources, of course - to get a simple but decent model and post train it intensely for just one language and one task.

For example doing backend projects using C# or Go.

mips_avatar

How did you guys set up the RL topology? Were you guys doing individual RL nodes (4xh200 rollout/4xh200 train) or did you have dedicated trainer and rollout nodes?

  • nblintao

    Dedicated rollout and trainer nodes, with RDMA transfers between them.

    • mips_avatar

      Do you guys support any unusual topologies? I’ve always wondered about maybe using an 8x rtx pro 6000 node for inference rollouts for cost.

octoberfranklin

FWIW that is about $331,000 on low-onboarding-grief clouds (e.g. vast.ai) right now using the SXM variants they used.

You might be able to shave that down using a different flavor of H200 (like PCIe) but it would take more hours, so benefits are unclear.

  • mips_avatar

    You'd probably end up spending more on pcie h200s. They're not that much cheaper than 8x sxm nodes and they only have 4 way nvlink. At the scale these guys were training at you'd probably want at a minimum an 8x nvlinked node for the trainer, even though you could technically fit the full training and optimizer states on a 4x h200 node.

  • lumost

    Savings would likely be larger with alternative accelerators such as trainium, no?

    • octoberfranklin

      Savings would likely be larger with magic beans such as floobarbaz, no?

      But seriously. If there were a cheaper and reliable way, I'm sure the authors would have mentioned it instead of H200 SXM modules. They're trying to brag about cheap training.

      Maybe you wanted to use an opportunity to shill tranium.

      • serf

        >But seriously. If there were a cheaper and reliable way, I'm sure the authors would have mentioned it instead of H200 SXM modules. They're trying to brag about cheap training.

        shit reasoning.

        the big dogs use all sorts of weird (usually better) shit because they have access to it.

        the opposite is also true. The H200 SXMs are available, some custom TPU purpose built for your needs isn't.

        or , in other words, "if there were they'd have done it!" begs us to believe the concept that everyone out there is doing things as optimally as possible, with perfect access.

      • phs318u

        > Maybe you wanted to use an opportunity to shill tranium.

        This was unnecessary and against HN guidelines to engage in good faith.

        • octoberfranklin

          No, and we get way too many low-effort "how does this compare to $FOO" comments that serve only to improve brand recognition of $FOO.

          Once you realize people are doing it you see it everywhere.

0x69420

3.8 27B is an interesting choice. on the face of it, doing RL on it feels like refrying twice-cooked pork then stuffing it in the microwave for good measure. the fact that even one benchmark (tb4.1) increased more than marginally is kind of miraculous. would be interesting to see where "miles" would take eg. 3.8 flash next, which is already impressive despite being an under-trained architectural preview.

  • Balinares

    I had the same thought. Their described process of identifying gaps and post-training on high-quality inputs specifically designed to close those gaps is very interesting. I wonder if that's possibly the secret ingredient in the frontier lab sauce.

robertkarl

I look forward to testing this against my private eval set to determine if it's benchmaxxing or actual improvement based on just 1200 tasks. downloading it now

  • robertkarl

    DaisyRose gets 2.5 points out of 100 more on my 86-task bench, than Qwen 3.8 Swift 1.5. at the cost of 5.5 hours vs. 7.8 hours for Daisy.

    swift run: 24GB VRAM / 4090 / llama.cpp / 5.5 hours / score 0.87 / medium reasoning / iq3_s / 128k context @ q4

    Daisy Rose: 48GB VRAM / A6000 / sglang / 7.8 hours / score .898 / medium reasoning / nvfp4 / 256k context at fp8

    pi for all tasks

    Daisy emitted 1.92M tokens and Swift 1.5 ... didn't. 1.04M there

    given multiple advantages in terms of kv cache size/quant, decode speed, time, and model quant: DaisyRose marginally beat out another base Qwen finetune running in half the VRAM.

    benchmaxxing imo.

    edit: formatting

XCSme

Is it post-training or bench-maxxing?

DeathArrow

Since some talented people with more modest means were able to do such a job, I wonder why Alibaba didn't do something like this when they trained the model.

They left a lot of performance on the table.

Which makes me wonder if such kind of optimizations are possible for other models like Deepseek v4.1 Flash 1017.

  • Balinares

    They did. Qwen 3.8 27b is a post-trained Qwen 3.6.

    Mind you, it's still bonkers how much runway 3.8 still had in it considering how implausibly capable it is for its weight.

Keyboard Shortcuts

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