I'm curious what people are building with these models

Rudybega an hour ago | parent | next [-]

I use it as a drop in replacement for LLMs I had previously doing filtering and classification in a pipeline. It's loads cheaper and faster with roughly equivalent performance on my own internal tests. The confidence scores (which are also reasonably well calibrated on my data) are a super nice bonus.

	▲	inerte a minute ago \| parent \| next [-]
		For me it's using 1 Jev call to ask 5 questions, instead of what I had before. What I had before was basically: - 1 classifier question - if ok, do some heavy computation - after heavy computation, another classifier So now what I do is: - Jev with the 1st and 3rd classifier - if ok, heavy computation I can classify many things at once, and it's cheaper and faster than 1 for sure and 1 maybe classification that I had before.
	▲	vanuatu an hour ago \| parent \| prev [-]
		^ Same here. so much faster and cheaper than using an LLM to return structured data

▲

nazgul17 2 hours ago | parent | prev | next [-]

Automatic tagging of images is what I'm doing with it. I'm using a modified Gemma model, which ingests images (and audio, for that matter).

▲

MisterMunchkin 10 minutes ago | parent | prev | next [-]

It’s good for automatically categorising or reviewing stuff which is free text.

▲

gopalv an hour ago | parent | prev | next [-]

You can turn a lot of process and workflow systems into deep decision trees.

My team hasn't finished writing their blog posts yet, but the customer demos [2] went out the moment TypeSafe took our call and sorted all the paperwork out.

There's a tiny section at the bottom of the demo which explains how it actually works (or the github repo is the code).

We have a single decision API[1] over all similar models, so we run evals across all the "System One" api products & definitely don't trust any benchmark that you haven't run. All standardized benchmarks have been benchmaxxed already.

PS: just in case it wasn't clear, the demo is a game where we play to calibrate the human vs machine decision making (or just do it in auto-pilot mode).

[1] - https://github.com/prasanthj/duckdb-dual-cognition

[2] - https://demos.isotopes.ai/demo/apps/chain-command

▲

LewisOrton an hour ago | parent | prev | next [-]

it's actually more usefull than it looks. it is not much useful on its own but it can play a big role in a complex workflow or custom harness.

i used luna 5.6 as the ranker/filter to remove useless items from upstream rag(mixing embedding, regex etc) and it did a good job but took 5-10 seconds each time. now less than 1 second and no observable precision loss. hope it helps

▲

ygouzerh an hour ago | parent | prev | next [-]

I found an example online, I cannot find the github again, but it was interesting: an instant dynamic generation of React component, you type what you want to build using natural language, and it directly add one to the page.

If I remember well, in the background, it does the multi-choice question: "What is the component requested ? --> Calendar, Slider, ..."

	▲	daviddoran an hour ago \| parent [-]
		https://shapeshiftui.vercel.app/ sounds similar.

▲

ASalazarMX 2 hours ago | parent | prev [-]

Judging from the tilte, I guess dreams.