Thread

1. alienbaby · 1790681869 · focus · HN ↗

   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 :)

   1. keepitwiel · 1790681896 · focus · HN ↗

      Bernoulli
   2. user3939382 · 1790682249 · focus · HN ↗

      If you want to get super pedantic about what’s happening in a transistor every digital Boolean is actually this

      1. kevindamm · 1790683117 · focus · HN ↗

         Not quite.. that boolean is about whether the voltage exceeds some threshold. It's not about how close the voltage is to the circuit's maximum possible threshold, or how much it exceeds the threshold.

         In an analog circuit, maybe.

         1. user3939382 · 1790734114 · focus · HN ↗

            Both the voltage and the threshold are probabilistic. Within a tight envelope sure. This is true even of the physical fields that comprise the transistor itself never mind the signal it’s designed to discretize. A more extreme example is a transistor hit with a stray gamma ray. When you dig deep enough there isn’t technically a Boolean anywhere, that’s a platonic construct that makes discussion of engineering convenient.

            1. kevindamm · 1790773127 · focus · HN ↗

               You specifically said "digital" in GGP comment. I took that to mean that you were choosing the abstraction above which those details matter. Yes, at the physical level all circuitry is effectively continuous and stochastic. Analog circuitry is the manipulation of these to give a more continuous state, digital circuitry uses voltage ranges and a forbidden middle to enforce a kind of noise immunity. When you dig deep enough that the noise is a point of concern, you are no longer looking at a digital Boolean.

               Just making sure we're being super pedantic.

   3. k__ · 1790684776 · focus · HN ↗

      The whole "no hallucinations" premise is based on that.

      Like, yeah, you don't hallucinate, but only because you force the user to decide in the end.

      1. rusk · 1790685484 · focus · HN ↗

         Wait til you hear about how digital circuits work at die level
      2. doginasuit · 1790685584 · focus · HN ↗

         That seems like the only possible way to eliminate hallucination, short of a model that is never wrong.
      3. kjs3 · 1790685765 · focus · HN ↗

         force the user to decide in the end

         And that's...bad?

         1. k__ · 1790691951 · focus · HN ↗

            Not entirely.

            I think, it's a bit much to call this "no hallucinations".

            Technically true, but in practice you could still choose the wrong result or the probabilities can be off.

   4. doginasuit · 1790685398 · focus · HN ↗

      I like it. It is short and distinct which is a good fit for a primitive. It describes its fundamental meaning and draws a connotation with Boolean.
   5. LudwigNagasena · 1790687979 · focus · HN ↗

      In Bayesian statistics that’s called credence. Weird that they felt the need to invent a new term.
   6. finding_alfred · 1790709351 · focus · HN ↗

      Jeeves pretended to understand. Is there data showing Jev's actually calibrated?

Unofficial Hacker News client; not affiliated with Y Combinator.