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

411–420 of 512 posts

Re: Introducing System One Models and Jev

#411

Post by somepatriot »

ramoz wrote: post #306
VladVladikoff wrote: post #303

Earlier quoted context omitted.

This is very cool. However I don’t really want to bounce all my home automation commands to the cloud. I hope there will be an open weights approach one day. I’ve spent a lot of time setting up my local only home automation system, it would suck if it didn’t work during an internet outage, and also there are obvious privacy problems.

GLiClass is performant, and its zero-shot classification scores are in the same ballpark as the Terra-level results Jev points to. https://github.com/knowledgator/gliclass

thanks, it's definetly relevant

Re: Introducing System One Models and Jev

#412

Post by mcintyre1994 »

cfowles wrote: post #268

Wasn't really till seeing this home assistant demo they have ( https://www.loom.com/share/18c4dbcf8db546dfb2d7f2ef018e78e4 ) that the value really clicked for me. Seems really cool.

That's a really nice demo and way more helpful than their website, thanks for sharing it!

Re: Introducing System One Models and Jev

#414

Post by mijoharas »

safeandsound wrote: post #400
mijoharas wrote: post #393

Earlier quoted context omitted.

Small request, can we get an explanation of the naming of "noul" in the docs[0]. I tried googling, and searching the docs and didn't understand why it was called that. (I'd also argue something like p_yes or just probability might be a simpler name, but I'm sure there's a better reason behind Bernoulli maps). [0] https://docs.typesafe.ai/primitives/noul#noul

Im going to guess bernoulli

It is Bernoulli (mentioned in the comment I replied to). I just failed to guess that myself :)

Re: Introducing System One Models and Jev

#415

Post by niutech »

paraschopra wrote: post #406

Cool approach, i think less latency and cost is the way to go. Here's how this would have likely been made. - Tiny transformer or equivalent model (maybe a few bn or so?), explaining latency and cost - Questions are sent in parallel to multiple copies of it (I'm sure they're edge located) - The model is post-trained for calibration in a wide variety of data (the recipe is relatively simple, and likely targeted on dis…

How does Jev compare with encoder language models like BERT/RoBERTa, which could also be used for classification?

Re: Introducing System One Models and Jev

#418

Post by lkm0 »

One application that sounds pretty interesting would be the creation of wikidata pages for anything. Plug a topic/word/concept/historical event in, take a bunch of wikidata properties, rephrase them as questions with the choices being the existing property values. Then feed it to LLMs or something. Does that make them more reliable? Probably not.

Re: Introducing System One Models and Jev

#419

Post by apexalpha »

throwaway314155 wrote: post #410
apexalpha wrote: post #381

Earlier quoted context omitted.

My smarthome has regular switches and wifi. There's no reason to not do both. Also a quick NFC sticker in each room taking you to a small HTML site containing settings (temp, ventilation, lights, shutters, setting a alarm by the lights) has been golden. No one wants to: download Shelly app + AC app + look for ventilation IR controller + figure out how casting works for the TV + figure out how to use the Shelly app to…

That's clever and all - solid setup, good work. But I still think you either overestimate the average house guest or have particularly savvy/young house guests.

Most people think it's cool but use it once.

The regular-ceiling-lights-as-alarm service gets positive feedback. Weird how smarthome companies never market that, seems easy win.

Re: Introducing System One Models and Jev

#420

Post by cgio »

WhitneyLand wrote: post #149
janalsncm wrote: post #113

Earlier quoted context omitted.

I don’t think it’s misleading if you compare on the use cases they suggested. It’s faster and cheaper (no idea if higher quality), so it’s immediately interesting for certain things. And if you buy their RLCD claims, this might be even better than huge models that know a bunch of irrelevant things.

What was misleading was the original title: "Jev: New frontier model 40-400x cheaper and 20-200x faster" I'm not the gatekeeper of who gets to call themselves a frontier model, but I don't think most people would count Jev in that group. It sounds false. If their specific claims hold up, then it would make more sense to say something like: "Advanced the speed/cost frontier for structured decisions"

It is frontier in the sense it is exploring an unexplored domain. I do agree on questioning the comparatives though. Speed/cost is indeed relevant for problems that can be framed as structured decisions only. The question is, would defining a structured decision model be a structured decision model itself? This would significantly increase the application domain.
Post reply on HN