Need help?
<- Back

Comments (61)

  • sharih
    What is the point of this, if it is p90 17 seconds? Might as well use an LLM. The beauty of Jev is that it is dirt cheap and insanely fast.
  • thm
    Ask Jeeves - Only took us 30 years to come full circle.
  • druskacik
    How's the performance compared to ordinary 9B LLM with structured outputs? Both accuracy and speed?
  • TN1ck
    I just did a run with a benchmark I just used to test other models against. (It's about detecting irony in german soccer tweets). On my M5 Pro with 48GB it took over 30min to decide on just 100 tweets, the thinking definitely takes long.It performed quite below Jev, but above other open decision models I tested (68 correct vs 79 correct for Jev - see [1]). I'm running it for the moderation benchmark as well, but that will probably take a few hours on my machine.[1] https://tn1ck.com/blog/jevdit
  • theanonymousone
    This reminds me of "on-premise cloud".
  • RamblingCTO
    Super dope. If it would ship as prod ready code supporting mps as well that would be even doper.But funny that jev is getting its lunch eaten apparently in under two weeks?
  • teravor
    you don't need to post-train anything for this.just get an LLM to think and then force it to output a specific json with prefill post-think.make sure to include good conditioning text in the prompt with examples of exactly what the output should be like. you don't want dissonance in the probabilities on the prefill.
  • swingboy
    Any good classifiers like this or Jev that support image input?
  • alienbaby
    Just curious, where has this term 'noul' come from for yes/no ansers?/a bit more digging and..A Noul performs a Bernoulli trial—an experiment with exactly two outcomes (yes or no)—but instead of picking one, it returns the calibrated probability (ranging from 0.0 to 1.0) that the statement is true.I hate it :)
  • swader999
    Seems like this is the way, a hybrid approach where some of the pipeline will be jev like and some traditional LLM depending on the nature of the work.
  • singularity2001
    In my experience, Jev is only faster because it's a small shitty model. Any objections?
  • loclol101
    How general really are these jev type models? Has anyone done any broad very cross-domain eval on them?
  • quantized_state
    The diffusion drafter adaptation is nice
  • zerop
    Are there "good" Open source Decision models built on Gemma-4 and also trainiable on own data?
  • woadwarrior01
    This isn't really surprising. LLM reasoning and before that, chain of thought prompting are essentially forms of test-time compute scaling.
  • Naitik88
    what about benchmark against smaller or bigger models? 9B looks too small for llm-level decisions.
  • mxkuzn
    interesting bench list, what about benchmark against smaller or bigger models? 9B looks too huge for small like laya, and too small for llm-level decisions.
  • captainbland
    See if it can beat Jev's Pokémon benchmark
  • AnodicElegy
    I'm surprised we haven't seen a "Jehovah" yet.
  • esafak
    Jev-like models give calibrated decision probabilities, but at low accuracy.So why didn't they show both??
  • phplovesong
    So "askjeeves" has been resurrected?
  • raverbashing
    Jeeves, that's a name I haven't heard in a long time...
  • hjun1052
    If the model does autoregressive reasoning before the decision, doesn't that give up much of what a Jev-style model buys you (a single forward pass, cheap calibrated probabilities)? Or is the point mainly to keep the typed output and probability interface while getting better accuracy on harder cases?