Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Introducing System One Models and Jev

typesafe.ai

Post reply on HN
Print view View original

151–160 of 513 posts

Re: Introducing System One Models and Jev

#151

Post by elcomet »

CompleteSkeptic wrote: post #141
WhitneyLand wrote: post #136

Earlier quoted context omitted.

His claim was that the title is misleading, not sure how it's relevant to that claim that you use "string models" (full LLMs). The original title before it changed less than an hour ago was: "Jev: New frontier model 40-400x cheaper and 20-200x faster" I'm going to agree that was misleading. And on the second point: >>Also "can't hallucinate" seems wrong? Sure, it can't emit an invalid type, but it can still emit a co…

> Type safety is not factual correctness. I very much agree with this and want to hone in on where do actually disagree. Would you say a linear classifier hallucinates?

Hallucinations were defined in the context of text generation models so your question does not really make sense.

IMO your system can make mistakes that are similar in spirit to hallucination (i.e. answering with a false answer instead of abstaining to answer).

Re: Introducing System One Models and Jev

#153

Post by CompleteSkeptic »

warpspin wrote: post #150

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

1. yes a general model 2. no training at all 3. but it is focused on "System 1" tasks (more human judgment, less math reasoning)

Re: Introducing System One Models and Jev

#154

Post by zenlikethat »

warpspin wrote: post #150

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

It's very generalized. Can't wait until everyone can see it.

Re: Introducing System One Models and Jev

#155

Post by vvzz »

jacobgold wrote: post #81

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 out…

I feel like the power of the approach presented here is that it gives a model a proper "language" to describe computations directly vs moving tape silliness.

I foresee this to be the path moving forward - giving AI models understanding of the computation directly(as well as compositional rules) This feels like a short path towards total software in many areas.

Re: Introducing System One Models and Jev

#158

Post by WhitneyLand »

CompleteSkeptic wrote: post #141
WhitneyLand wrote: post #136

Earlier quoted context omitted.

His claim was that the title is misleading, not sure how it's relevant to that claim that you use "string models" (full LLMs). The original title before it changed less than an hour ago was: "Jev: New frontier model 40-400x cheaper and 20-200x faster" I'm going to agree that was misleading. And on the second point: >>Also "can't hallucinate" seems wrong? Sure, it can't emit an invalid type, but it can still emit a co…

> Type safety is not factual correctness. I very much agree with this and want to hone in on where do actually disagree. Would you say a linear classifier hallucinates?

Let's say classifiers don't hallucinate. To make a fair comparison we should constrain LLMs to the same classification task. In that case, no, LLMs also don't hallucinate.

- Give Jev and LLM the same input

- Lock down both to approved/rejected/unknown (LLM restricts on decoding)

- Both can be wrong, but neither can hallucinate (invent an another option).

Re: Introducing System One Models and Jev

#159

Post by zenlikethat »

himata4113 wrote: post #16

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!

It's a bit hastily put together, but I made a dspy fork where you can add a decorator to automatically use TypeSafe where possible on Signatures. It shows a fair bit of what actual, hands on usage looks like.

https://github.com/typesafeainate/dspy-typesafeify

Post reply on HN