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

Computer use in Gemini 3.5 Flash

blog.google

Post reply on HN
Print view View original

41–50 of 175 posts

Re: Computer use in Gemini 3.5 Flash

#41

Post by dr_dshiv »

mitchell_h wrote: post #25
satvikpendem wrote: post #2

There's still no MCP support in the Gemini app, which is very useful to get various pieces of info as a user just via chatting. For example I recently wanted to get an Airbnb and wanted to filter by specific criteria including house image analysis and Gemini couldn't do it so I had to do it in Codex.

I'm fairly convinced Claude's strongest point is the app. AI users aren't anywhere near as mature or smart as youtube/hn would have folks believe. The claude app is amazing for bridging that gap.

Didn’t it take them like 2 days to build the first one?

Re: Computer use in Gemini 3.5 Flash

#42

Post by jubilanti »

thorum wrote: post #22
airstrike wrote: post #4

Computer use is such a terrible idea. It's slow, insecure, error prone, expensive. I guess if you're trying to get people to tokenmaxx it may look like a valid strategy, but ain't no way this will be delightful to users. I think it's a symptom of just not understanding how LLMs should interface with the OS because we're still in their early days. Eventually there'll be an iPhone moment for the ergonomics of LLM usage…

The “correct”, elegant way for AI to interact with existing software would take decades and billions of dollars to build. Someone would have to do the hard work of building new APIs, solving decades of accessibility issues, etc. Or you can show an AI screenshots and ask it where to click.

it takes decades and billions of dollars to develop APIs?

Re: Computer use in Gemini 3.5 Flash

#43

Post by Chu4eeno »

revolvingthrow wrote: post #28

People using google’s models: am I holding it wrong or are the guardrails really overtuned? I had the dubious pleasure of testing gemini of late and I kept running into refusals. How do I transfer a sim number from one provider to another? No. What should I consider when making backups on ntfs less prone to data loss and more bitrot resistant? No. Evaluate this piece of code? No. I’m not sure if it’s cold feet from t…

I've always found all versions of gemini to be (for a lack of a better word) lazy.

I guess it's economic wrt. token use, but it often either refused for absurd safety reasons, or other weird stuff like responding that an LLM like itself wasn't a suitable tool for the job, and very quickly gives up.

Claude is on the other end of the spectrum, which makes it more noticeable when switching between them.

Re: Computer use in Gemini 3.5 Flash

#44

Post by Chu4eeno »

chatmasta wrote: post #32
sarreph wrote: post #23

Earlier quoted context omitted.

I disagree if your application is networked. Most SaaS is built on RESTful APIs that can be converted trivially into interfaces / contracts for tool use.

So you can either wait for every application to do that, or at least make it possible for an LLM to do it… or you can make the LLM use a computer interface that works with every application by definition.

The middle ground would be leveraging e. g. standard a11y APIs, and/or hooking into applications like Squish does.

Then you get a nice textual world that fits the LLM without having to rewrite every application to have a fullblown HTTP server.

Re: Computer use in Gemini 3.5 Flash

#45

Post by airstrike »

orbital-decay wrote: post #30
airstrike wrote: post #4

Computer use is such a terrible idea. It's slow, insecure, error prone, expensive. I guess if you're trying to get people to tokenmaxx it may look like a valid strategy, but ain't no way this will be delightful to users. I think it's a symptom of just not understanding how LLMs should interface with the OS because we're still in their early days. Eventually there'll be an iPhone moment for the ergonomics of LLM usage…

Spreadsheet is such a terrible idea. It may look like a valid tool, but ain't no way it's delightful to users. Most of the time people need a database instead. Eventually there'll be an iPhone moment for this. Meanwhile, the entire world economy:

I mean, your words not mine. You can't just claim I'm making a point I didn't.

Spreadsheets are fucking glorious, powerful, clever, amazing and delightful, in my view.

Re: Computer use in Gemini 3.5 Flash

#46

Post by airstrike »

gdudeman wrote: post #26
airstrike wrote: post #4

Computer use is such a terrible idea. It's slow, insecure, error prone, expensive. I guess if you're trying to get people to tokenmaxx it may look like a valid strategy, but ain't no way this will be delightful to users. I think it's a symptom of just not understanding how LLMs should interface with the OS because we're still in their early days. Eventually there'll be an iPhone moment for the ergonomics of LLM usage…

Computer use is a great idea. It gets the job done when nothing else will. If you're a person trying to get their job done at a big company, but half your job is in 1-2 proprietary tools or is stuck behind an API you can't program against, computer use can allow you, a non-techie, to do your job more efficiently. I think it's an awesome way to circumvent gate keepers and the IT department to let people accomplish the…

That is an incredibly niche use case and comes with a boatload of footguns.

Even then, an AI writing AHK scripts likely outperforms.

Re: Computer use in Gemini 3.5 Flash

#47

Post by dyauspitr »

airstrike wrote: post #4

Computer use is such a terrible idea. It's slow, insecure, error prone, expensive. I guess if you're trying to get people to tokenmaxx it may look like a valid strategy, but ain't no way this will be delightful to users. I think it's a symptom of just not understanding how LLMs should interface with the OS because we're still in their early days. Eventually there'll be an iPhone moment for the ergonomics of LLM usage…

We shouldn’t optimize for token use. We should build infrastructure to make tokens dirt cheap instead.

Re: Computer use in Gemini 3.5 Flash

#48

Post by reacharavindh »

gdudeman wrote: post #26
airstrike wrote: post #4

Computer use is such a terrible idea. It's slow, insecure, error prone, expensive. I guess if you're trying to get people to tokenmaxx it may look like a valid strategy, but ain't no way this will be delightful to users. I think it's a symptom of just not understanding how LLMs should interface with the OS because we're still in their early days. Eventually there'll be an iPhone moment for the ergonomics of LLM usage…

Computer use is a great idea. It gets the job done when nothing else will. If you're a person trying to get their job done at a big company, but half your job is in 1-2 proprietary tools or is stuck behind an API you can't program against, computer use can allow you, a non-techie, to do your job more efficiently. I think it's an awesome way to circumvent gate keepers and the IT department to let people accomplish the…

How are folks using “computer use” to click things on intranet portals that are behind an SSO? Even this OP example shows visitors a url and enter this search term… that is port of useless.

How can I automate things behind an SSO wall? Even if it means I manually authorize it once and watch it do things on its own..

Re: Computer use in Gemini 3.5 Flash

#50

Post by WarmWash »

revolvingthrow wrote: post #28

People using google’s models: am I holding it wrong or are the guardrails really overtuned? I had the dubious pleasure of testing gemini of late and I kept running into refusals. How do I transfer a sim number from one provider to another? No. What should I consider when making backups on ntfs less prone to data loss and more bitrot resistant? No. Evaluate this piece of code? No. I’m not sure if it’s cold feet from t…

Are you outside the US?
Post reply on HN