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

Gemini 2.5 Computer Use model

blog.google

Post reply on HN
Print view View original

191–200 of 339 posts

Re: Gemini 2.5 Computer Use model

#191

Post by stronglikedan »

dekhn wrote: post #71

Many years ago I was sitting at a red light on a secondary road, where the primary cross road was idle. It seemed like you could solve this using a computer vision camera system that watched the primary road and when it was idle, would expedite the secondary road's green light. This was long before computer vision was mature enough to do anything like that and I found out that instead, there are magnetic systems that…

> I concluded that my approach was just far too complicated and expensive.

Motorcyclists would conclude that your approach would actually work.

Re: Gemini 2.5 Computer Use model

#192

Post by poopiokaka »

alach11 wrote: post #188
dekhn wrote: post #71

Many years ago I was sitting at a red light on a secondary road, where the primary cross road was idle. It seemed like you could solve this using a computer vision camera system that watched the primary road and when it was idle, would expedite the secondary road's green light. This was long before computer vision was mature enough to do anything like that and I found out that instead, there are magnetic systems that…

Computer use is the most important AI benchmark to watch if you're trying to forecast labor-market impact. You're right, there are much more effective ways for ML/AI systems to accomplish tasks on the computer. But they all have to be hand-crafted for each task. Solving the general case is more scalable.

Not the current benchmarks, no. The demos in this post are so slow. Between writing the prompt, waiting a long time and checking the work I’d just rather do it myself.

Re: Gemini 2.5 Computer Use model

#193

Post by Spooky23 »

y0eswddl wrote: post #136
chrisfosterelli wrote: post #116

Earlier quoted context omitted.

Ironically now that computer vision is commonplace, the cameras you talk about have become increasingly popular over the years because the magnetic systems do not do a very good job of detecting cyclists and the cameras double as a congestion monitoring tool for city staff.

and soon/now triple as surveillance.

Those cameras aren’t usually easily or cheaply adapted to surveillance. Most are really simple and don’t have things like reliable time sync. Also, road jurisdictions are really complex and surveillance requires too much coordination. State, county, town, city all have different bureaucratic processes and funding models.

Surveillance is all about Flock. The feds are handing out grants to everyone, and the police drop the things everywhere. They can locate cars, track routine trips, and all sorts of creepy stuff.

Re: Gemini 2.5 Computer Use model

#194

Post by fragmede »

Macha wrote: post #151
apwell23 wrote: post #146

Earlier quoted context omitted.

yes i bike on chicago lakefront up and down is like 40 miles for me. also biking on roads you should never count on sounds to guide you. you should always use vision. for example, making a left you have to visually establish that driver coming straight has made eye contact with you or atleast looked at you. can you share a example of how you are using sound to help you ride bikes with other vehicles on the road? are…

The sound of a revving engine is often the first warning you have that someone is about to pass you and especially how they handle it is a good sign of how likely they are to attempt a close pass rather than overtake in the legal manner with the minimum distance.

That doesn't work for EVs. Situational awareness is important, don't rely on any one thing,

Re: Gemini 2.5 Computer Use model

#195

Post by tech234a »

btbuildem wrote: post #181

Does it work with ~legacy~ software? Eg, early 2000's Windows WhateverSoft's Widget Designer? Does it interface over COM? There's a goldmine to be had in automating ancient workflows that keep large corps alive.

“The Gemini 2.5 Computer Use model is primarily optimized for web browsers, but also demonstrates strong promise for mobile UI control tasks. It is not yet optimized for desktop OS-level control.”

Re: Gemini 2.5 Computer Use model

#196

Post by fragmede »

fn-mote wrote: post #176
dhon_ wrote: post #142

Earlier quoted context omitted.

I was concerned there might be sensitive info leaked in the browserbase video at 0:58 as it shows a string of characters in the browser history: nricy.jd t.fxrape oruy,ap. majro 3 groups of 8 characters, space separated followed by 5 for a total of 32 characters. Seemed like text from a password generator or maybe an API key? Maybe accidentally pasted into the URL bar at one point and preserved in browser history? I…

This is the kind of response that makes me feel like we are getting left behind by the LLM. Very nice solve, ChatGPT.

We're cooked.

Re: Gemini 2.5 Computer Use model

#197

Post by nerdsniper »

dekhn wrote: post #71

Many years ago I was sitting at a red light on a secondary road, where the primary cross road was idle. It seemed like you could solve this using a computer vision camera system that watched the primary road and when it was idle, would expedite the secondary road's green light. This was long before computer vision was mature enough to do anything like that and I found out that instead, there are magnetic systems that…

My town solved this at night by putting simple light sensors on the traffic lights so as you approach you can flash ur brights at it and it triggers a cycle.

Otherwise the higher traffic road got a permanent green light at nighttime until it saw high beams or magnetic flux from a car reaching the intersection.

Re: Gemini 2.5 Computer Use model

#198

Post by fragmede »

emp17344 wrote: post #149
pseidemann wrote: post #121

Earlier quoted context omitted.

Funny thing is, most humans cannot properly control a computer. Intelligence seems to be impossible to define.

Is this a joke, or do you actually believe most people are incapable of using a computer?

We should be very specific and careful with our words. pseidemann said "most humans cannot properly control a computer", which isn't the same as "most people are incapable of using a computer".

I would agree with pseidemann. There's a level of understanding and care and focus that most people lack. That doesn't make those people less worthy of love and care and support, and computers are easier to use than ever. Most people don't know what EFI is, nor should they have to. If all someone needs from the computer to be able to update their facebook, the finer details of controlling a computer aren't, and shouldn't be important to them, and that's okay!

Humanity's goal should have been to make the smartest human possible, but no one got the memo, so we're raising the bar by augmenting everyone with technology instead of implementing eugenics programs.

Re: Gemini 2.5 Computer Use model

#199

Post by nerdsniper »

dktp wrote: post #98
dekhn wrote: post #71

Many years ago I was sitting at a red light on a secondary road, where the primary cross road was idle. It seemed like you could solve this using a computer vision camera system that watched the primary road and when it was idle, would expedite the secondary road's green light. This was long before computer vision was mature enough to do anything like that and I found out that instead, there are magnetic systems that…

I cycle a lot. Outdoors I listen to podcasts and the fact that I can say "Hey Google, go back 30sec" to relisten to something (or forward to skip ads) is very valuable to me. Indoors I tend to cast some show or youtube video. Often enough I want to change the Youtube video or show using voice commands - I can do this for Youtube, but results are horrible unless I know exactly which video I want to watch. For other se…

https://www.ycombinator.com/companies/blue

Re: Gemini 2.5 Computer Use model

#200

Post by poopiokaka »

serf wrote: post #154
ramoz wrote: post #18

This will never hit a production enterprise system without some form of hooks/callbacks in place to instill governance. Obviously much harder with UI vs agent events similar to the below. https://docs.claude.com/en/docs/claude-code/hooks https://google.github.io/adk-docs/callbacks/

>This will never hit a production enterprise system without some form of hooks/callbacks in place to instill governance. knowing how many times Claude Code breezed through a hook call and threw it away after actually computing the hook for an answer and then proceeding to not integrate the hook results ; I think the concept of 'governance' is laughable. LLMs are so much further from determinism/governance than people…

You can obviously hard code a hook
Post reply on HN