34 comments

  • nl 2 hours ago
    Do you have any examples or data on the discriminatory power of the model for tool use?

    The examples are things like "What is the weather in San Francisco", where you are only passed a tool like

      tools='[{"name":"get_weather","parameters":{"location":"string"}}]',
    
    I had a thing[1] over 10 years ago that could handle this kind of problem using SPARQL and knowledge graphs.

    My question is how effective is it at handling ambiguity.

    Can I send it something like a text message "lets catch up at coffee tomorrow 10:00" and a command like "save this" and have it choose a "add appointment" action from hundreds (or even tens) of possible tools?

    [1] https://github.com/nlothian/Acuitra/wiki/About

    • michelsedgh 11 minutes ago
      Thanks to a Huggingface linked below, I tested it and im not impressed. prmopt: i need to contact my boss i will be late. Result: 20mins [{"name":"set_timer","arguments":{"time_human":"20 minutes"}}]. It didnt use the email tool and i tried 2-3 different ways of asking it.
  • ilaksh 7 hours ago
    Hmm.. this might make it feasible to build something like a command line program where you can optionally just specify the arguments in natural language. Although I know people will object to including an extra 14 MB and the computation for "parsing" and it could be pretty bad if everyone started doing that.

    But it's really interesting to me that that may be possible now. You can include a fine-tuned model that understands how to use your program.

    E.g. `> toolcli what can you do` runs `toolcli --help summary`, `toolcli add tom to teamfutz group` = `toolcli --gadd teamfutz tom`

    • HenryNdubuaku 7 hours ago
      So Needle is trained for INT4, what you see in the playground is INT4, only 14MB, same challenge though.
      • ilaksh 7 hours ago
        Oh gotcha. Fixed my comment.
  • simonw 6 hours ago
    Suggestion: publish a live demo of the "needle playground". It's small enough that it should be pretty cheap to run this on a little VPS somewhere!
    • quantumleaper 6 hours ago
      Should be quick and easy with WebGPU, too.
      • simonw 6 hours ago
        That's an even better idea, I bet this could run in Transformers.js.
      • ilaksh 6 hours ago
        Good idea. Could you make that.
        • bijowo1676 1 hour ago
          Good idea. Could you ask a Claude Code to make that.

          Today is 2026 after all

    • HenryNdubuaku 6 hours ago
      thanks, yeah, the problem is just handling scale, we don't have the infra ready to go, but anyone can do that. Its easy for people to run on their laptops straight up. Will try the VPS route.
  • kristopolous 6 hours ago
    That M versus B is way too subtle. 0.026B is my suggestion
    • DrammBA 46 minutes ago
      I was so confused by many comments in this post but thanks to you I realized that some people are apparently reading it as 26B and that's why their comments make no sense.
    • bigyabai 2 hours ago
      The "M" nomenclature has been around since at least BERT and T5/FLAN. It's valid to use it even if today's LLM devs are more familiar with billion-scale models.
    • HenryNdubuaku 6 hours ago
      Haha, we were trying to not be hand-wavy too much :)
    • dymk 4 hours ago
      [flagged]
      • dang 46 minutes ago
        Can you please make your substantive points without sharp elbows? We're trying for something different here, and would appreciate it if you'd post in the intended spirit.

        https://news.ycombinator.com/newsguidelines.html

      • kristopolous 3 hours ago
        Pardon me, do I know you?

        Why are you attacking me?

        • osrec 2 hours ago
          I don't think they're attacking you, but suggesting you read more carefully. The information provided is correct and clear, but you need to let go of your own biases when consuming it.

          I personally prefer the M to the B. I guess as an engineer, noticing the units comes pretty naturally.

          • kristopolous 1 hour ago
            20-30 Billion is expected these days, there's many models of this size, it's very common.

            Advertising something that's 1/1000th that is significant and remarkable, hiding it in a single letter is burying the lede

      • f33d5173 3 hours ago
        I read it as 26B as well.
  • brainless 3 hours ago
    Lovely to see the push for tiny models.

    I have been building for small (20B or less) models for quite a while. Highly focused/constrained agents, many of them running together in some kind of task orchestration mode to achieve what feels like one "agent".

    I build (privacy first) desktop apps this way and I want to get into mobile apps with similar ideas but tiny models.

  • tomaskafka 4 hours ago
    Awesome! I just tried to set an alarm and add some groceries to the shopping list, and it outperformed Siri.
  • kgeist 2 hours ago
    >Experiments at Cactus showed that MLPs can be completely dropped from transformer networks, as long as the model relies on external knowledge source.

    Heh, what a coincidence, just today one of my students presented research results which also confirmed this. He removed MLP from Qwen and the model still could do transformation tasks on input but lost knowledge.

  • exabrial 3 hours ago
    Dumb questions, from someone not in the field...

    What is a distilled model?

    Why doesn't Google do this (to make their models smaller)?

    Seems like you could make a competitor to Gemini?

    • HenryNdubuaku 3 hours ago
      No question is stupid!

      1. Distilled means taking the intelligence of a big model and compacting into a tiny model.

      2. Google already does so with FunctionGemma, but Needle argues that better performance could be achieved with 10x smaller model using our technologies.

    • tintor 3 hours ago
      Model distillation is lossy compression of big model to produce a smaller model.

      Smaller model requires less space on disk, less video memory, and less compute (cheaper hardware).

      Downside is that distilled model performs worse on the same benchmarks compared to original model.

  • efskap 2 hours ago
    No FFN is blowing my mind. This is pretty much "Attention Is ACTUALLY All You Need". Reminds me of BERT Q&A which would return indices into the input context, but even that had a FFN. Really exciting work.
    • krackers 48 minutes ago
      I guess this had always been bugging me. I get while you need activation/non-linearities, but do you really need the FFN in Transformers? People say that without it you can't do "knowledge/fact" lookups, but you still have the Value part of the attention, and if your question is "what is the capital of france" the LLM could presumably extract out "paris" from the value vector during attention computation instead of needing the FFN for that. Deleting the FFN is probably way worse in terms of scaling laws or storing information, but is it an actual architectural dead-end (in the way that deleting activation layer clearly would be since it'd collapse everythig to a linear function).
  • simonw 7 hours ago
    Looks like you need to open up access to https://huggingface.co/Cactus-Compute/datasets/needle-tokeni... - I get this error when trying to run the steps in your README:

    > Repository Not Found for url: http s://huggingface.co/api/datasets/Cactus-Compute/needle-tokenizer/revision/main.

  • bityard 5 hours ago
    This is pretty much exactly what I want for Home Assistant. I yell out, "Computer! Lights!" and it toggles the lamp in the room on or off. (I mean I can do that now, I think, but probably with a much larger model.)

    I haven't played with it yet, but does it ever return anything other than a tool call? What are the failure modes? What if it doesn't understand the request? Does it ever say it can't find a tool? Does it get confused if there are two similar (but different) tools? Can it chain tools together (e.g. one tool to look up and address and another to get directions to the address)?

    I mean, I plan on downloading the model later tonight and finding out for myself, but since I'm stuck at work right now, I figured I'd ask anyway...

  • alex7o 4 hours ago
    From all the models that do toolcalls the only thing I am confused is why did you pick the worst? Or maybe they are only bad in agentic work it fine for one shot toolcalls?
    • HenryNdubuaku 4 hours ago
      Gemini is pretty solid for 1-shot tool call and affordable as well.
      • BuyG1n 2 hours ago
        Hi, would love to know where you get that impression on 1 shot tool calling, was there concrete evaluation carried out? pretty new to this and was a bit lost when trying to compare models on different capabilities.
  • Havoc 6 hours ago
    Sounds interesting.

    Got a bunch of errors trying to run it on CPU though. Very likely connected to me running this in a container (unpriv LXC), but figured for 26M CPU would suffice.

    https://pastebin.com/PYZJKTNk

    • dakolli 6 hours ago
      It better, considering its purpose is to run on devices with no GPU.
  • rsolva 5 hours ago
    Can it summarize text it fetches?

    Come to think of it, this could be a nice model to have as the first pass in a more complex agent system where Needle hands of the results of a tool call to a larger model.

    I will defiantly play around with this!

    • NordStreamYacht 2 hours ago
      > I will defiantly play around with this!

      Are you Calvin or Hobbes?

    • HenryNdubuaku 5 hours ago
      The codebase is fully open, feel free to play around!
  • z3ugma 4 hours ago
    I don't really understand what this is for... there is a lot of ML-researcher talk on the GH page about the model architecture, but how should I use it?

    Is it a replacement for Kimi 2.7, Claude Haiku, Gemini Flash 3.1 lite, a conversational LLM for the situations where it's mostly tool-calling like coding and conversational AI?

    • HenryNdubuaku 4 hours ago
      It is for building agentic capabilities into very small devices like phones, glasses, watches and more. Does that make sense?
      • jcgrillo 3 hours ago
        I'm having trouble understanding why someone would want that? Like, what are the product use-cases of such a thing? I understand why people want that for coding agents--although the jury is still very much out on whether those are terribly useful--but I cannot fathom what someone might want an agent to do on a cell phone? Is there some user-facing activity on a phone that's similar to coding with a tight, objectively measurable feedback loop (analogous to dev/compile/test)?

        EDIT: more of you cretins have downvoted than have replied.. so.. show your cards.

        • jasonjmcghee 1 hour ago
          Throwing a few things out - HN has changed over the years, but people make stuff to make stuff. There don't need to be product use cases. The tone of the comment goes against the spirit of HN - likely the reason for downvotes.

          That aside- a very small model that takes text and outputs structured json according to a spec is nice. It let's you turn natural language into a user action. For example, command palettes could benefit from this.

          If you can do a tiny bit of planning (todo) and chain actions, it seems reasonable that you could traverse a rich state space to achieve some goal on behalf of a user.

          Games could use something like it for free form dialog while stool enforcing predefined narrative graphs etc.

          I'm sure you could come up with more. It's a fuzzy function.

          • jcgrillo 54 minutes ago
            > people make stuff to make stuff. There don't need to be product use cases.

            OK. Great! So it doesn't need to be a commercial product. But does it do something (anything?) interesting? I'm interested in your games example, I'd love to see it done in real life. IIUC, game AIs are actually much more constrained and predictable for play-ability reasons. If you let it go all free form a plurality of players have a "WTF??!?" experience which is super Not Good.

            • digdugdirk 23 minutes ago
              It doesn't have to do any thing interesting - it's completely fascinating all on it's own. If you understand anything about the math and science behind LLMs, you'll understand that this is an achievement worthy of sharing to a community like HN.

              That being said, small models like these have plenty of use cases. They allow for extra "slack" to be introduced into a programmatic workflow in a compute constrained environment. Something like this could help enable the "ever present" phone assistant, without scraping all your personal data and sending it off to Google/OpenAI/etc. Imagine if keywords in a chat would then trigger searches on your local data to bring up relevant notes/emails/documents into a cache, and then this cache directly powers your autocomplete (or just a sidebar that pops up with the most relevant information). Having flexible function calling in that loop is key for fault tolerance and adaptability to new content and contexts.

              Its cool. Enjoy it.

              • jcgrillo 15 minutes ago
                > Something like this could help enable the "ever present" phone assistant, without scraping all your personal data and sending it off to Google/OpenAI/etc

                OK so show me what that's for. Show me something useful you can do with that ability.

                > Imagine if keywords in a chat would then trigger searches on your local data to bring up relevant notes/emails/documents into a cache, and then this cache directly powers your autocomplete (or just a sidebar that pops up with the most relevant information).

                I'm really trying but.. idgi? I truly cannot imagine how this would improve my life in any way...

                > Its cool. Enjoy it.

                No. It sounds like a useless complication on my watch. I don't fucking care if it can tell me the phase of the moon. I can look up at the sky and see the moon and know what phase it is.

        • HenryNdubuaku 3 hours ago
          You can think of “phone use” for instance, what Siri is supposed to be.
          • jcgrillo 3 hours ago
            I mean.. Siri basically works? When I'm driving I say "Hey Siri, find me a gas station along my route", and it does. Or I say "Hey Siri, call Joe Bob mobile" and it does. Or I say "Hey Siri, play me a podcast". This is kind of a solved problem already? When I'm driving this is literally as complicated of a distraction as I want--I'm not going to be dictating emails or texts. When I'm not driving, the touchscreen keyboard (as shitty an interface as that is) is 100x better than voiced natural language commands.
            • ilaksh 3 hours ago
              It does just barely work now after they spent billions, and they may still fall back to cloud LLMs for a significant number of things. This is a way that everyone can get that on the actual Apple Watch or local phone for any application they build.
              • jcgrillo 2 hours ago
                I get that, but I still can't imagine what it might be for. TBH I don't have a smart watch, because I can't think of anything I'd want one for--my mechanical watch keeps time to within a few seconds per month and the lume lasts all night. I don't know what making it "smarter" would do for me, it does an A+ job of being a watch. What are the things that "everyone" can build with this that actually matter? Like, what is the differentiator?

                EDIT: To be clear, the monoculture of phone operating systems sucks. If this somehow enables more entrants into that space then I'm all for it. However, I don't see this in particular being the deciding factor... For example, the reason I don't run a 3rd party operating system on my phone isn't because it's lacking Siri or "OK Google" (if these things went away tomorrow I'd barely notice), it's because it would be a pain in the ass to make it be a phone.

  • murkt 6 hours ago
    Can this be a Siri-like core? Set me a timer, tell me what’s the weather, etc. Here is transcribed text and available list of tools for the model to call, and voice the output.
  • logdahl 6 hours ago
    I find this stuff super fascinating and been thinking about it myself. Maybe one could bootstrap tiny models on a rather 'pure' procedural data set. Neglecting [0] of course...

    [0]: http://www.incompleteideas.net/IncIdeas/BitterLesson.html

    • HenryNdubuaku 5 hours ago
      Sounds interesting, would love to see it too!
  • zamalek 5 hours ago
    Is the idea here to add function calling to models that don't have it, or even improve function calling (qwen quirks)?
    • HenryNdubuaku 5 hours ago
      So it’s a tiny model capable of function calling that could run locally on cheap devices.
  • sroussey 2 hours ago
    Can this be converted to onnx or otherwise be used in a browser?
  • syntaxing 3 hours ago
    This would be amazing for home assistant.
    • synesthesiam 3 hours ago
      On my list to check out tomorrow :D
      • syntaxing 1 hour ago
        Wow can’t believe the voice engineer lead for Nabu Casa is here! Super excited to see if this works for HA!
      • HenryNdubuaku 3 hours ago
        Thanks, keep me posted!
  • quadrature 5 hours ago
    Does the model have capacity for in context learning ?, if we give it examples of patterns can it follow them ?.
    • HenryNdubuaku 5 hours ago
      Not yet, for now. But it’s in the works!
  • dangoodmanUT 4 hours ago
    Why pick Gemini? It's probably the worst tool calling model of the major labs.
  • roggenbuck 4 hours ago
    This is some excellent work Henry! Very excited to try it out.
  • cmrdporcupine 6 hours ago
    This is very cool I'm going to try to carve out some time to try building this into my MOO system ( https://codeberg.org/timbran/moor / https://timbran.org/moor.html ) as alternative command parser front end.
    • Balinares 6 hours ago
      Man, I love that there are still people writing new MOO servers in 2026. Any game out there already running on mooR?
      • cmrdporcupine 5 hours ago
        Many people tease that they will, and start... but then kinda stop. But mostly just been building my own bespoke thing on my own bespoke platform, and kinda running out of steam because I need to make $$ instead.
    • HenryNdubuaku 6 hours ago
      Thanks, let us know how it goes!
  • deepsquirrelnet 6 hours ago
    This is really cool. Any plans to release the dataset?
    • HenryNdubuaku 5 hours ago
      We include the dataset pipeline in the codebase so far, might release dataset.
  • theykk 3 hours ago
    hey nice work, is it possible to release the datasets?
    • HenryNdubuaku 2 hours ago
      We have so far released the dataset generation code
  • varispeed 4 hours ago
    What is the use case for this?
    • HenryNdubuaku 4 hours ago
      Deploying AI on tiny devices like watches, earphones, glasses etc.
      • varispeed 3 hours ago
        Ok, but why? What is the use case?
        • chris_money202 3 hours ago
          I don't think the limit is just on tiny devices. It can also be used in apps on generic computers, because its so small anything can run it reasonably quick.

          For example, I am thinking this could be helpful for say if you have a complicated build and test infrastructure, fine tune this model on that infrastructure and then people can say more generic things like build and run this library's test, rather than issuing the exact commands to do that or going to Claude, GHCP, etc

  • BoredPositron 5 hours ago
    I source old, defective high-end radios with timeless designs from brands like Grundig or Braun, and replace the original hardware with a Raspberry Pi while using the original audio parts to build custom smart speakers. Reliable hotword detection and voice command recognition have been a persistent challenge over the years, but whisper and other small models have helped enormously. At the moment I have ollama running on my server with qwen 9b which works fine but a 26M that could be deployed on the pi itself would be amazing.
    • HenryNdubuaku 4 hours ago
      Sounds cool, play with it and let uk know what you think!
  • BuyG1n 2 hours ago
    [dead]
  • nhattruongadm 6 hours ago
    [flagged]
  • danelliot 4 hours ago
    [dead]
  • abhijithbabu 8 hours ago
    [flagged]
  • ac29 6 hours ago
    FYI, distilling Gemini is explicitly against the ToS:

    "You may not use the Services to develop models that compete with the Services (e.g., Gemini API or Google AI Studio). You also may not attempt to reverse engineer, extract or replicate any component of the Services, including the underlying data or models (e.g., parameter weights)."

    • Havoc 6 hours ago
      Yeah I think Google should shove that somewhere. They effectively distilled all the internet's knowledge into these models...without asking & without permission
    • HenryNdubuaku 6 hours ago
      Thanks, Needle doesn’t compete with those tools though and the distillation process did not access the weights.
    • ilaksh 6 hours ago
      I think GLM 5.1 or Kimi 2.6 could substitute for this type of purpose.
    • iAMkenough 5 hours ago
      FYI, Gemini was developed using stolen copyrighted works without author consent. The double standard is striking.
    • ForHackernews 6 hours ago
      So is copying all the books in the world.
    • vablings 6 hours ago
      Oh no! They stole the model weights! Distillation "attacks" is such bullshit
    • xgulfie 6 hours ago
      This is being downvoted but it's worth noting if only for the "be careful" aspect.

      That said, we need more people distilling models IMO, just be ready for a C&D and a ban