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

Fara-7B: An efficient agentic model for computer use

github.com

Post reply on HN
Print view View original

21–30 of 92 posts

Re: Fara-7B: An efficient agentic model for computer use

#21

Post by serf »

codezero wrote: post #2

Are there any agentic models like this that would work for controlling input in arbitrary video games? I've been wanting to have an AI play Kerbal Space Program because I think it would just be pretty hilarious.

> I've been wanting to have an AI play Kerbal Space Program because I think it would just be pretty hilarious.

people have been experimenting with this since early Opus days.

Check out kRPC. Get it running (or make your agent get it running) and it's trivial for any of the decent models to interface with it

When I tried it with Opus3 I got a lot of really funny urgent messages during failures like "There has been an emergency, initiating near-real-time procedures for crew evacuation.." and then it's just de-couple every stage and ram into the ground.

Makes for a fun ant-farm to watch though.

[0]: https://krpc.github.io/krpc/

Re: Fara-7B: An efficient agentic model for computer use

#23

Post by ilaksh »

ghrjfjfnnfn wrote: post #15

Forgive me if I can't keep up with the latest AI bubble mania buzzwords, but what is "agentic" even supposed to mean? As far as I can tell it doesn't have a precise definition, and doesn't even sound like proper English.

It means it is trained/tuned for function (tool) calling (e.g. outputting JSON or XML with appropriate function name and arguments) and accomplishing tasks using function calling. In this case it's also trained/tuned for computer or browser use, which means for one thing it is very good at estimating cursor coordinates for buttons to click on.

Re: Fara-7B: An efficient agentic model for computer use

#24

Post by AYBABTME »

ghrjfjfnnfn wrote: post #15

Forgive me if I can't keep up with the latest AI bubble mania buzzwords, but what is "agentic" even supposed to mean? As far as I can tell it doesn't have a precise definition, and doesn't even sound like proper English.

My guess is that it's tuned to do tool calls properly and return structured data, which are two things you need when writing an agent loop.

Re: Fara-7B: An efficient agentic model for computer use

#26

Post by yousif_123123 »

pogue wrote: post #14

Why does Microsoft keep releasing models trained on synthetic data? Is it possible their contract with OpenAI won't let them do anything else? I would think Microsoft, of all companies, would want to be working on their own LLM behind the scenes, even if they're relying on OpenAI for the bulk of their work. Meta seems to be the only US company releasing big 'open source' models, while Chinese companies continue to re…

Perhaps they want to be able to run them on mobile hardware they release?

Re: Fara-7B: An efficient agentic model for computer use

#28

Post by btbuildem »

If I'm reading this correctly, it's limited to browser use, not general computer use (eg, you won't be able to orchestrate KiCAD workflows with it). Not disparaging, just noticing the limitation.

I've been playing with the Qwen3-VL-30B model using Playwright to automate some common things I do in browsers, and the LLM does "reasonably well", in that it accelerates finding the right ways to wrangle a page with Playwright, but then you want to capture that in code anyway for repeated use.

I wonder how this compares -- supposedly purpose made for the task, but also significantly smaller.

Re: Fara-7B: An efficient agentic model for computer use

#29

Post by brianjking »

btbuildem wrote: post #28

If I'm reading this correctly, it's limited to browser use, not general computer use (eg, you won't be able to orchestrate KiCAD workflows with it). Not disparaging, just noticing the limitation. I've been playing with the Qwen3-VL-30B model using Playwright to automate some common things I do in browsers, and the LLM does "reasonably well", in that it accelerates finding the right ways to wrangle a page with Playwri…

Correct, this only works in the browser w/ Playwright as far as I can tell from a quick test.

Re: Fara-7B: An efficient agentic model for computer use

#30

Post by pogue »

yousif_123123 wrote: post #26
pogue wrote: post #14

Why does Microsoft keep releasing models trained on synthetic data? Is it possible their contract with OpenAI won't let them do anything else? I would think Microsoft, of all companies, would want to be working on their own LLM behind the scenes, even if they're relying on OpenAI for the bulk of their work. Meta seems to be the only US company releasing big 'open source' models, while Chinese companies continue to re…

Perhaps they want to be able to run them on mobile hardware they release?

I can definitely see them wanting to have models that can run on Windows computers or Surface tablets locally - although their focus seems to be sticking CoPilot into absolutely anything and everything possible, but why synthetic data models? Other companies have made small parameter models, but they don't seem to keep them up to date (correct me if I'm wrong).
Post reply on HN