HN

Comments (215)

• Menu

  jacobgold
  First, congrats to the team on launching something genuinely interesting and new.Seems like a more accurate title would be "Jev: Trading general purpose generation for fast typed inference" or something like that.This is interesting, but the speed comparison seems misleading? A generative model that can output code in a Turing-complete language can do anything a computer can do.Jev can only generate structured output, right? This is probably super useful for classification/routing/scoring, but it's nothing like the code generating models we're all using today for code and automation.Also "can't hallucinate" seems wrong? Sure, it can't emit an invalid type, but it can still emit a completely wrong valid value. You can enforce structured output from an LLM too, with an appropriate harness, etc.Assuming there's no funny business, the Doom demo is cool.
• maltalex
  This is a very promising idea - a model that takes arbitrary text input (which can be a complex json), plus a set of questions (yes/no, multiple-choice, or score) and quickly (milliseconds) and cheaply ($0.042/MTok) answers those questions.Unfortunately, none of this is explained in the announcement, but the documentation [0] is pretty good.[0]: https://docs.typesafe.ai/concepts/how-to-build-with-system-o...
• altcognito
  If it is so cheap, why such a limited release?
• Menu

  futurisold
  This, combined with contracts, could make a lot of things so much fun now!For those who don't know (which is probably everyone but me), I ported the design-by-contract pattern in Python and combined it with LLMs. This was early 2025. I originally wrote about it here: https://leoveanu.com/2025-03-01-dbc/ . Contracts are a core feature of SymbolicAI ever since. The community seems to have loved it too (https://news.ycombinator.com/item?id=44399234).I think I'm starting to glimpse the implications and it's gonna change agentic workloads if it holds up to scrutiny. It's too early for me to tell anything other than jot down some rough thoughts.In short, you get blazingly fast semantic branching you can use in control flows. For contracts, I can now directly take the data model that you have to design and convert it into Jev's expected format. Or I can use Jev for semantic branching in postconditions.If my understanding is correct, that should be doable, but I need to think more about it. It could be that with Jev I can finally “compile contracts” and better chain them into workflows, which is something I always wanted but didn't know how to do properly.Eager to test. On the waiting list.
• Menu

  big_toast
  It seems like the docs[0] are a better explanation? The comparison to llm tokens is kinda confusing.It looks like the model takes as input a state (structured text? not sure if multi-modal) and a question (as a "Choice", "Score", or "Noul") with some additional augmentations possible. Then outputs the question's answers as appropriate (e.g. a choice, accompanying probabilities, confidence).Edit: On the AI primer page, it looks like they do the RLCD on a pre-trained base model?[0]:https://docs.typesafe.ai/concepts/system-one
• Menu

  dgellow
  Side note: it took me more time than I would like to admit to realize that Diogo Almeida isn’t a satirical version of the name Dario Amodei
• bregmandiv
  I'm trying to parse it down to what we had before vs what is new here.We already had encoder models that skipped text generation for giving us a numerical output that could be computed as a probability. we also got no hallucinations and faster inference for free there. So we already had1. "unstructured state in, probabilistic decisions out" 2. "orders of magnitude faster and more efficient"What was hard there was to train the model head without ML expertise, and considerable amount of data.This seems like this is a democratization of those encoders? The addition over existing encoders seems to be coming from being able to specify the output shape (up to a cardinality of 255). It is unclear to me if this is possible using Jev without additional labels for fine-tuning.If so, that is still very impressive, but I think the faster inference and 0 hallucinations might come for free, from it not being generative.
• Menu

  lubujackson
  After much fumbling around with prompts and evals, this is exactly how I am using LLMs in production, to narrowly make choices and return structured data. Any deterministic work gets pulled out of the prompt and my goal is to narrow the model output to be as clearly defined and as minimal as possible.Jev's focus on structured I/O and confidence scores are game changing. If this does at all what it claims, I think this is going to quickly become the new standard approach for agentic systems.
• Menu

  skerit
  So in theory you could feed it incomplete text, and then ask it for the probabilities of what the next character could be?
• Menu

  ramon156
  This sounds good but so far all claims just sound like marketing terms. I'd love to see real proof. e.g. "RLCD" and "parallel sampling" have nothing to back it up.also "70-500ms vs 3-329 seconds" are apples-to-oranges unless the LLM baseline is doing comparable work (e.g., long chain-of-thought). If Jev is skipping generation entirely for a narrow structured task, of course it's faster.Nonetheless i want this to be true, so I'm looking forward to JevEdit: I really have to say that I like their manifesto https://typesafe.ai/manifesto
• Menu

  mushufasa
  I would love for things like this to be accessible via hubs like open router or AWS bedrock. It's hard to justify adding new model vendors directly with all the heightened concerns about privacy and security, but if bold new capabilities are added to a centralized already-vendor like AWS, technical people can adopt them without going through a whole compliance/purchasing/vendor review process. And an extra middleman tax is well worth it when the cost savings of the model itself can be one-two orders of magnitude.
• abeppu
  I think this is a great direction -- for some kinds of users. And this makes me wonder if the 'vs' framing is misleading.Yes, I think it's a mistake that many organizations are cramming LLMs inside of automated pipelines where the extreme generality/flexibility of the model is at odds with the fact that you're using it for a very specific task that gets repeated over and over, and needs a very specific structured output to be successful. But specifying your task carefully (as well as deciding what counts as your input state representation etc) seems like a form of programming. Something (a person or a model working in a relatively unrestricted way) will need to produce a configuration/specification for this system.So rather than Jev vs Claude I imagine that using Claude/ChatGPT/whatever interactively to define / refine your Jev config which then runs in prod might be the happy combination?
• Menu

  alphazard
  There's a whole lot of information on this page that doesn't tell me anything about what this actually is. Can anyone spell out what the architecture is here?They claim it's not an LLM, which I read as "not an auto-regressive token generator". I assume they are still using a transformer, otherwise they would be talking about the thing that's not a transformer, instead of all the fluff on the linked page. But they emphasize parallel generation, so is it like a text diffusion model?
• Menu

  jawns
  I could see this being fantastic for classification tasks. Last year I shifted from using LLMs for bulk data classification tasks (1M transcripts) to generating embeddings and categorizing based on cosine similarity. It saved a ton of costs and time, but wasn't as accurate as LLMs. This seems like it can give me Terra-level classification ability with the cost/speed I need.
• Menu

  dinobones
  This is a good product but the naming/branding is pretty unfortunate.Typesafe.AI sounds like some typescript/structured output type of tool…What even is “system one” ?IMO the product/tech is really there, just needs better communication.
• bjconlan
  You know you're too old when you see the company name and think! Oh I wonder what Martin Odeskey , Jonas Bonér and co are up to. Wait, didn't they become lightbend... Altho this comment takes away from what these guys are doing which legitimately sounds interesting.
• filearts
  If we could come up with a system to classify the probabilities across a large number of candidate words (or components thereof) then this could actually be good at producing text, one element at a time. We could call these elements 'tokens' and picking the right one could be called something like 'decoding'. Crazy idea but hear me out...On a more serious note, it will be fascinating to see how this different spin on modelling inference will create new paradigms or slot into existing ones.
• Menu

  xynelius
  The Doom demo looks impressive but was it a fine-tuned model? It's the difference between a cool demo and revolutionary tech.
• Menu

  albelfio
  https://x.com/completeskeptic/status/2099925682726002904?s=4...The doom demo is quite cool
• Menu

  vatsachak
  It could be used for coding if you gave it an AST.If you work at TypeSafe please try this.Side note: This is probably how LLMs would perform with better encoders and next-latent prediction, so eventually those will beat this architecture out. Still amazing though.
• postalcoder
  This has the potential to be huge for computer use.OpenAI has been teasing how fast computer use is with their models running on Cerebras chips but the difference here is a burning hole in your pocket.
• _boffin_
  Any relation / inspiration to GLiClass?
• mixtureoftakes
  Doom demo is beyond impressive, even scary
• cooljoseph
  A few questions:1. Do you provide any kind of largest common subtree caching for cheaper input?2. Have you tried auto-generating Lisp programs structurally?3. Have you tried augmenting a Lisp language with a `choice` function that makes choices given a prompt, the environment, and the continuation stack?
• Menu

  bqsile
  If it work as good as they say it does, confidence score + really fast response when you want very fast response, basically.. To me it is a crime against humanity to not open source it. Just get the money from cloud inference and cloud agentic sessions or whatever but open source it. This tech, a good harness, a good model provider, and you have basically a AGI building machine.
• Menu

  wxw
  > Input tokens: $0.042 / MTok ($42 per billion tokens).> Output tokens: FREE (too cheap to meter).Insane. The video demos are really compelling, in particular the speed.> Structured outputs slot into ordinary software as fuzzy decision rules: classify, route, score, extract, or branch where hand-written logic is too brittle. The surrounding code constrains their freedom, making them easier to compose into reliable systems.I buy this vision. A lot of LLM integration I see these days is ultimately exactly this. OpenAI-style structured outputs works decently but this would be a great improvement in cost, latency.
• tylermarques
  We had early access and found it to be pretty useful. Having a second form of verification, where you can ask multiple questions (in the form of Nouls) raised our confidence in the outputs of other models. [0] IMHO This type of model works incredibly well in concert with LLMs, not as a replacement.[0] https://goodstartlabs.com/research/verification-is-the-bottl...
• Menu

  himata4113
  They never show exactly how they use it? Only a bunch of animations of it 'working'. Would like to see the actual code used for the demos!
• Menu

  warpspin
  Haven't seen any docs or so. Is this actually a general model, or does it need training on the the data set it answers? Finding it suspicious you never see some kind of prompt.Edit: never mind, found https://docs.typesafe.ai/introduction/quickstart by now
• Menu

  initsecret
  > [others] Output tokens: ~5x more expensive than input tokens.> [them] Output tokens: FREE (too cheap to meter).I'm very confused by this.
• hoppp
  This is amazing. I really could use this.I like the idea of System one models but all LLMs so far work as system 1 thinking because humans generate speech subconsciously with system 1.System 2 thinking requires consciousness which AI does not have, so even reasoning models are still system 1 thinking as system 1 in humans has reasoning with heuristics.Its limited but most people navigate the world with it completely, so it's enough for AI.
• Menu

  torginus
  I was thinking about something similar (maybe) - generally speaking, embeddings for LLMs tend to learn real world concepts - things like 'fruit' or 'France' or 'city' as directions in embeddings.But in things like programming, most concepts are abstract - 'if hungry eat an apple' in programming terms would look like'if hunger > 50 {apples--; hunger-=30;}'and compilers work with 'concept erasure' - to them, tokens (which are like llm tokens) look like'if var1 > 50 {var2--;var1-=30}'.They don't care about how these things map to real concepts. So all the embedding directions used to encode real-world concepts are just noise to LLMs when programming. This greatly reduces dimensionality and training costs. So does a token representation tuned for programming constructs, rather than natural language would probably have a more efficient encoding.
• tensegrist
  what is the…epistemic status, for lack of a better way to put it, of the probabilities? what do they mean? what (probabilistic) guarantees do we have about, say, the responses to- is the capital of france paris?- it is august. is it raining in paris?(forgive the examples; they're probably not semantically the sort of thing jev is trained to work on. but i figure the point translates to various kinds of questions that come up in "inner loop of agentic pid controller" contexts)a normal text-generating model if asked to produce a number will also do that just fine. i assume in jev's case it was actually rled to essentially learn to express priors over things using its implicit world model, which definitely ought to help, but can we say more?
• Menu

  2001zhaozhao
  Hasn't there been a lot talk about Astra's opaque reasoning capabilities (being able to think through complex questions without using a chain of thought)?Given that, can't you just replicate Jev by telling Astra "here is the question, you must make a multiple choice decision / output a score between 1-10, please answer directly in a single word, no reasoning allowed"?(Edit: Ok, Jev is much cheaper in input tokens so these two aren't directly comparable at all)
• Mentlo
  Hm, would be good to understand the architecture better. Is this answering just from a world model informed prior? How informed is it by the information in the prompt? I can't see this maintaining calibration across all domains and all types of structured output.Is there anything published on how it maintains calibration? Or when you say "outputs calibrated probabilities" you mean "as calibrated as frontier LLM models, just cheaper" - which is a different claim; as LLM's aren't particularly well calibrated
• anon
  undefined
• johnecheck
  This makes me think of Expressions of Change [1], a project that aimed to make updates to a program a first-class primitive in a programming language. A model like this can't output code directly, but perhaps it would be well suited to select from the small set of discrete operations on code envisioned by the EoC author?[1]: www.expressionsofchange.org
• Menu

  whazor
  A question I have, with the type { output: string }, would the model not become a LLM? And if it does, shouldn’t it cost the same as a LLM for output?
• 2001zhaozhao
  Funny how the authors are asserting that "doing the right task > data > compute > algorithms" while simultaneously releasing AI model for calibrated decision making, which if they work, would mean that "compute > doing the right task"
• preommr
  This will be insane for tool usage, and probably where the major economics for day-to-day usage will be.The goal is going to be to use llms to distill operations down to some dsl, and pass it into something like Jev.
• woggy
  Can this be used in conjunction with a text-generating LLM for better quality code generation?
• theredsix
  Congrats on the launch! What's different between Jev and Microsoft's Guidance package? https://github.com/guidance-ai/guidance Is it a diffusion generator under the hood?
• Gecko4072
  From the person in the video regarding issues with benchmarks in general, and for LLMs. Also their approach. Good article.https://substack.com/home/post/p-215252866
• Menu

  moffers
  So is it a structured data-based language model? Or is there a model and a harness? Hopefully they’ll open up and explain more.
• findjashua
  Would it be fair to say that this is tailored for tool-selection subagents?
• Menu

  kart23
  This makes me kind of nervous for the whole AI thing now. Are people gonna lose their jobs, etc.? so much of the economy is now built on top of LLMs.
• tidewave
  Congrats on the release!Finetuning a language model for decision classification (with probabilities) is already well-understood. What specifically changes in the training objective with RLCD? Are its benefits isolated from Jev’s new architecture/parallelism?
• Menu

  adroitboss
  I am positive I know exactly how this works, I made something similar a few months back. But the problem is without generation you are extremely limited in the use cases. And while the model can't hallucinate, it can still be wrong. It just can't make up data.
• jrickert
  Signed up for the beta! :) would love to put this through some real-world shootouts against traditional LLMs to see where this type of model really excels.I’m guessing it might be able to replace maybe 40-70% of LLM calls for a given pipeline depending on the business task, cutting the API costs on those calls by an order of magnitude.
• Menu

  sim04ful
  This sort of stuff almost sends shivers down my spine, it's like i'm looking 5 years into the future.
• jceg
  > We deliberately chose not to publish performance against public benchmarks. In fact, we plan to only have one-off evals when we make product updates.lol, I bet they would publish them if their score on those benchmarks were good.
• Havoc
  Will need hands on to truly tell, but the doom demo seems very promising. If it can play that with text descriptions of where stuff is by distance and degrees in a 3D context then many GUI automation tasks should be easily doable
• scottyah
  Wild that it doesn't generate text. I wonder how its technology compares to Tesla's FSD stack.
• pixelmelt
  Interesting concept, I can't see a reason to use a generalist classifier over an api rather then just training my own? If it was open weights I would probably mess around with it.
• Menu

  petesergeant
  This is basically a zero-shot classifier that can accept raw text (or structured text) as an input, and is able to classify that text as accurately (they claim) as a frontier-level LLM. I have workflows this would be useful for, looking forward to it showing up on OpenRouter.
• gok
  So... a classifier model?
• Menu

  entrep
  This puts the human even more out of the loop I'll guess?
• Menu

  bthornbury
  Is the tradeoff of the parallel output that we don't get arbitrary string generation? like output # of tokens is fixed ahead of time?Either way, really cool and impressive.
• ernsheong
  This is potentially huge and can crash the Big Two's stock prices or block their IPOs completely.
• elcomet
  The technology and the results are very handwavy. What is RLCD exactly ? What are scores on benchmarks compared to LLMs ?This website does not inspire confidence at all, it all sounds like a marketing piece. I wish it was true, some kind of text-prompted classifier with LLM performance would be cool, but I can't trust it with what we are given.
• _davide_
  What's the difference compared to just taking an embedding and feed forward a simple net trained for the task?
• anon
  undefined
• zmmmmm
  The eval is baffling me> we assume there is a correct compute graph (a “workflow” represented in code) and use the predictions of the largest, smartest, and most expensive external models as reference probabilities. ... Rephrased: every model gets the same workflow. We test how they compare to the average of the smartest models (in this case, Astra and Fable).They assume there is a correct graph, but they don't compare to that, they compare to the average of the smarts models? So the smartest models are getting it wrong but you compare that anyway as a benchmark? So the outcome is "how much of a Fable am I getting" etc. Why not compare the actually correct thing?But then even on this hand constructed eval, the first plot is showing Jev at less than Sonnet 5 accuracy. It is barely better than Luna. There are two Opus 5's and two Sonnet 5's without explanation. What is the plot showing?I gave up.
• Menu

  pennomi
  > Extraordinary claims require extraordinary evidence so see below for the receipts.Yes, that’s the kind of attitude I want to see in these model releases
• Menu

  darksaints
  Okay, so it doesn't output text, that much is understood. What are the inputs like? I'm assuming maybe a text input? maybe an AST definition? Really hard to tell how this works at all from the demos, especially since we can't really try it out.
• hi_hi
  If I’m understanding correctly, this will work well for self driving cars?
• Menu

  andai
  Why did they pick the name System One? It's not really explained what "System One tasks" and "System One shaped queries" are. Things that need a fast response?Does this imply it's a very small model? I couldn't find anything about the model itself.
• pama
  Is there a downloadable technical report somewhere?
• bfeynman
  Super intrigued by this - large scale automation using LLMs is quite annoying due to deprecation cycles of models from frontier labs and cost of running your own being prohibitive when you have a blend of them.
• Menu

  seinecle
  Can this be used in practice to write code?
• poly2it
  Is there a bottleneck which would hinder putting this architecture in charge of a humanoid? Would it be able to operate continuously, for example in conjunction with an LLM for long-term reasoning? Doom seemingly works extremely well.
• bananaflag
  Funny how it can do everything but not chat. Sort of how when I was a kid I thought of a medicine that could cure any disease except the common cold.
• hspeiser
  this might finally be smart enough and fast enough for jarvis. hard to feel like iron man when your assistant takes 8 seconds to decide to pause your music
• Menu

  totallygeeky
  Woof, that page is hard to read. I don't understand what they've done to the way text is rendering but it's not great for my eyes.
• erichocean
  I could put this to use today.I think we'll see a bunch of different architectures over the next five years.
• bilsbie
  I’m not understanding what this is. It’s a faster cheaper LLM?
• kylehotchkiss
  "While Jev gives up string generation, it’s optimized for structured outputs and can’t hallucinate"Ouh! Any open weights models that can do this yet?? If not, how much longer? I have a Mac Studio coming soon.
• Menu

  hunterbrooks
  um what is going on with the outfit changes in the launch video...https://x.com/CompleteSkeptic/status/2099925682726002904
• yieldcrv
  oooooh it can play Doom!forget LLM benchmaxxing sidequests, I'm sold on the real benchmark
• Menu

  charcircuit
  Parallel inference where you don't want a subagent seems niche. But there is a lot of random things where businesses ultimately want some kind of score instead of generating something.I think the interesting thing would be seeing if prompt injections still work with this kind of model.
• whalesalad
  What is it about the rendering of this page that is so... off? It almost looks like the entire thing is a <canvas> element.edit: looks like a framer export where there is a text stroke being applied :|
• esafak
  Looks like a great model for NLP.
• yieldcrv
  this is interesting, so not an LLM but can be used in these use cases that LLM's have been shoehorned intohttps://docs.typesafe.ai/concepts/use-case-map
• larodi
  "is this the real thing or is just fantasy"
• kypro
  > Outputs> LLMS > Strings / generated text. Strings are flexible and can be anything: chat responses, code, hallucinations, refusals, or even type-safe structured values. To be used by software, responses need to be parsed + validated. There is also always some risk that the AI goes off the rails.> Jev > Type-safe structured values. Possible outputs and structure are defined in advance. The model never makes type errors. All answers are accompanied with calibrated probabilities and confidence scores.I mean, this isn't even remotely comparable to LLMs so why compare? Also, why are they bringing up AGI given there approach is so restrictive that what they're building literally cannot have the creativity required for AGI? The video is 100% marketing slop...The bulk of the application of LLMs is that they generate reasonably reliable text which doesn't need to be defined in advanced. I'm sure there is a niche for this and congrats to the team, but please let's not hype this as if it's the next big thing in AI...
• mkrishnan
  If this is true means, AI Stock bubble burst. (For good)
• quotemstr
  It looks like a specialized encoder-only(-ish) transformer with scalar and ordinal output heads. Acausal in effect, maybe? Probably not even autoregressive?I'd use this as a tool an LLM can use for specialized tasks. It's not AI in itself.
• mlcruz
  [dead]
• hofo
  [dead]
• mkrishnan
  If this is true, then AI Stock Bubble burst (for Good)