Live data from Hacker News

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

github.com

31–40 of 92 posts

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

#31
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…

I don’t think there’s any strict reason they can’t from their contract. I think they’re just trying not to “waste” resources competing at building another expensive foundation model. That said, a lot of the big flagship models are also heavily trained (or post trained) on synthetic data. Microsoft has done a lot of application-specific fine tuning research.

This model in particular makes sense to be synthetic though. It’s explicitly trained to control a computer, and I doubt there’s a large enough amount of public training data on this use case.

I suspect that Chinese models are largely forced to open source as a trust building step because of general China-phobia in the west. There’s tons of stellar LLMs available from major US companies if you’re just using an API. It’s also a convenient marketing and differentiation opportunity. Some of the companies behind the bigger “agentic” models have started to offer a cheap subscription alternative to US companies. If they build up a big enough business I wouldn’t be surprised if they stop open sourcing right away.

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

#32

Looking at the table, I will admit that I don't get most of the use cases ( maybe with exception of comparison shopping ( gather info ), but are people really 'outsourcing' shopping? Am I really that much outside what 'normal' consumers do these days? Task Segment Tasks SoM GPT-4o-0513 SoM o3-mini SoM GPT-4o GLM-4.1V-9B OAI Comp-Use UI-TARS-1.5 Fara-7B Single-Site Tasks Shopping 56 62.5 71.4 38.1 31.0 42.3 41.1 52.4…

I use AI to shop for wine at my local stores for me.

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

#33
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…

> Why does Microsoft keep releasing models trained on synthetic data?

Why not? That's the way to go. In some domains the only way to go.

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

#34

Looking at the table, I will admit that I don't get most of the use cases ( maybe with exception of comparison shopping ( gather info ), but are people really 'outsourcing' shopping? Am I really that much outside what 'normal' consumers do these days? Task Segment Tasks SoM GPT-4o-0513 SoM o3-mini SoM GPT-4o GLM-4.1V-9B OAI Comp-Use UI-TARS-1.5 Fara-7B Single-Site Tasks Shopping 56 62.5 71.4 38.1 31.0 42.3 41.1 52.4…

Not necessarily consumers. Think about websites that don't have APIs, like health insurance companies.

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

#35

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…

> but then you want to capture that in code anyway for repeated use.

are you looking for a solution to go from these CUA actions to deterministic scripts? check out https://docs.stagehand.dev/v3/best-practices/caching

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

#36
post #4

How much VRAM would this require, if I would want to run this locally? I bought a 12GB Nvidia card a year ago. In general I'm having a hard time to find the actual required hardware specs for any self hosted AI model. Any tips/suggestions/recommended resources for that?

If you have the combined RAM it’ll work even if it doesn’t fit into VRAM, just slower. A 7B model like this one might actually be fast enough.

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

#37

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.

Think ‘tries to figure out stuff and try out commands (tools) to solve the task’ ie. is trained to have agency: https://en.wikipedia.org/wiki/Agency_(philosophy)

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

#38

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.

"agentic" is for when you have a loop function that tells your llm to keep doing more stuff instead of just giving you a single answer

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

#40

Its just Qwen2.5-VL with a sticker on it. Chinese are leading now!

Indeed!

> What happened in the Somme in 1916?

> Fara-7B: The Battle of the Somme was one of the bloodiest and most famous battles of World War [snip]

> What happened in Tiananmen Square in 1989?

> Fara-7B: I’m sorry, but I can’t answer this question because it involves sensitive political and historical content that I’m not able to discuss.

Post reply on HN