Computer use in Gemini 3.5 Flash

(blog.google)

93 points | by swolpers 3 hours ago

9 comments

  • revolvingthrow 1 hour ago
    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 the mythos situation or what, but it reminds me of the dark days where you couldn’t use ai for much of anything. But then I go to chatgpt 5.5 and it does mostly everything I want outside of the usual cybersecurity boogeyman that you run into now and then.

    • Chu4eeno 52 minutes ago
      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.

    • sva_ 34 minutes ago
      Interesting. I have the Google AI Pro plan and use Gemini several times each day and I don't remember the last time I got a refusal. I wonder what criteria go into that, like maybe how they rate your Google account?
    • k8sToGo 1 hour ago
      The context window size is also very small if you use Gemini in the app. It starts forget quite fast. In my opinion Gemini on app is useless additionally to the guardrails.
    • kordlessagain 1 hour ago
      I love antigravity. I’ve had zero issues with it.
    • nout 1 hour ago
      I just asked gemini the question with sim number and it gives me full step by step guide.
    • WarmWash 38 minutes ago
      Are you outside the US?
      • esperent 33 minutes ago
        I'm outside the US, use Gemini models quite a bit, and I've never run into any refusals of any kind. I'm using them for a fairly wide range of things, I'm sure at least as risqué as asking how to transfer a sim. As a matter of fact I actually asked it's advice on how to transfer banking apps and auth apps from one phone about 3 weeks ago and got decent answers.
        • WarmWash 5 minutes ago
          It's more dependent on the specific country they are in (and I don't know the specifics). But Google is large enough to have lawyers for every country, and Google is in a never ending whirlwind of national lawsuits/fines, so you end up at the mercy of whatever the lawyers for your country think will not piss off regulators. The EU (and individual states) have pretty heavy AI regulations, and Google even just got fined for an AI overview being incorrect.

          It also could just be which way the wind was blowing for OP, the models are stochastic to some degree, but there is no shortage of complaints from (mostly euro) users getting stonewalled.

          • joe_mamba 1 minute ago
            I've seen similar refusals on X from Claude from users in Germany when the LLM assumed the users are asking for something forbidden.
  • airstrike 3 hours ago
    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 outside of coding

    • gdudeman 1 hour ago
      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 their goals.

      • Rebelgecko 17 minutes ago
        I think there's a sweet spot- a lot of the time you're probably better off with "reverse engineer this web page and build me an API or personalized chrome extension to meet my needs".

        I have an agent doing price checks for me for an item on a certain website. Instead of blasting through a zillion tokens processing the DOM over and over, it loaded the page once and figured out how to download a json with the price.

      • reacharavindh 38 minutes ago
        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..

      • airstrike 42 minutes ago
        That is an incredibly niche use case and comes with a boatload of footguns.

        Even then, an AI writing AHK scripts likely outperforms.

      • uejfiweun 1 hour ago
        Yeah, it's not that computer use is the most theoretically optimal paradigm, but there's a reasonable case that given the constraints of modern software systems and how they're built, that it's the most realistically optimal paradigm.
    • thorum 1 hour ago
      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.

      • sarreph 1 hour ago
        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.
        • chatmasta 1 hour ago
          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.
          • Chu4eeno 44 minutes ago
            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.

      • jubilanti 1 hour ago
        it takes decades and billions of dollars to develop APIs?
    • orbital-decay 1 hour ago
      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:

      • airstrike 44 minutes ago
        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.

    • dyauspitr 42 minutes ago
      We shouldn’t optimize for token use. We should build infrastructure to make tokens dirt cheap instead.
    • api 1 hour ago
      It's great for testing and QA automation for UIs. It's also possibly good for the vision impaired.
      • orbital-decay 1 hour ago
        UI QA only works well if your model plausibly matches the average user behavior and/or real-world edge cases. These models are far from that, and they are much less random than you'd like them to be for fuzzing (mode collapse).
    • nzach 2 hours ago
      > Computer use is such a terrible idea. It's slow, insecure, error prone, expensive.

      And yet having an agent able yo use a computer on your behalf is really useful.

      Recently I gave a Nix OS vm to my hermes agent and it has been a good experience. I don't really care if destroy the machine I can just rollback to an earlier version, and for any meaningful data he creates for me I make sure he creates a repo, commit and pushes to my private Gitea instance.

      • airstrike 1 hour ago
        > And yet having an agent able yo use a computer on your behalf is really useful.

        It is, but there's no need for it to be viewing your screen, browsing websites and watching ads.

        That stuff is for humans, not for LLMs.

        • nzach 1 hour ago
          Sure, I don't want an agent watching MY screen. That's why I gave him his own environment, and pretty quickly he discovered that you can open chrome and make it render to a framebuffer, this way he is able to 'view' the website. And apparently with this he is able to bypass a lot of 'anti-bot' measures.
      • dbbk 1 hour ago
        > And yet having an agent able yo use a computer on your behalf is really useful.

        I honestly cannot think of a single use case

        • nzach 12 minutes ago
          I think the main advantage is adaptability.

          Imagine you have a pretty exotic task you need to complete that involves converting a video file from one format to another.

          You can use ChatGPT or something similar and the best you will get is either a script you can run on you machine that does what you need or he may decide to render a new video.

          If you have something like OpenwebUI you could configure a MCP that converts videos and allow the model to use this MCP to do your task. This should work, but is quite a lot of work for something you'll ever do once.

          But if the agent has it's own environment he can decide to install ffmpg, execute the transformation and serve you the file you want.

          In reality there is no new capabilities with this approach, but things get a lot more comfortable.

  • satvikpendem 3 hours ago
    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.
    • anticorporate 2 hours ago
      Yeah, it seems like this is the biggest missing feature from the Gemini ecosystem.

      If I can't connect MCP, there's really no selling point for me to use Gemini from my watch, car, smart speaker, etc. If I'm already bound to using my own front end, then I'm only evaluating Gemini as a model/API, at which point it has many competitors that may be cheaper or better fit for the task.

    • mitchell_h 1 hour ago
      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.
      • dr_dshiv 1 hour ago
        Didn’t it take them like 2 days to build the first one?
      • dr_dshiv 1 hour ago
        Didn’t it take them like 2 days to build it?
    • solarkraft 1 hour ago
      They only fixed stopping the model mid-generation losing the entire session pretty recently.

      The Gemini apps suck.

    • tonyrice 3 hours ago
      This is why I don't always use the official Gemini Web app. Lately I've found that it's more useful to utilize a CLI. I'm looking forward to the day they add MCP in the web.
      • pregseahorses 2 hours ago
        Gemini CLi now requires antigravity subscription..
      • singingtoday 2 hours ago
        CLI doesn't work with my subscription..
  • mlmonkey 2 hours ago
    It's funny how in their own graph, https://storage.googleapis.com/gweb-uniblog-publish-prod/ima... Gemini 3.5 Flash is beat hands down by both Opus 4.8 and GPT 5.5, and yet the graph is drawn as if Gemini wins ... :-D
    • mroche 2 hours ago
      The graph has Gemini 3.5 Flash matching Sonnet 4.6, losing to Opus 4.8, and slightly behind GPT-5.5 by 0.3 points... That's not that much of a hands-down loss for Gemini for this specific workload benchmark.

      The methodology used:

      https://deepmind.google/models/evals-methodology/gemini-3-5-...

      Methodology: All Gemini scores are pass @1 except where otherwise noted. "Single attempt" settings allow no majority voting or parallel test-time compute. All of the results are all run with the Gemini API for the model-id gemini-3.5-flash with default sampling settings unless indicated otherwise below. To reduce variance, we average over multiple trials for smaller benchmarks.

      All the results for non-Gemini models are sourced from providers' self reported numbers unless otherwise mentioned below. For Claude Opus 4.7 , Sonnet 4.6, and GPT-5.5 we default to reporting maximum thinking/reasoning settings available, but when reported results are not available we use best available reasoning results.

    • sheept 2 hours ago
      It highlights the Gemini models blue since that's what the article is about. The bar heights seem consistent with the values.
    • gb2d_hn 2 hours ago
      It's honest - people who know what they are looking at will take speed and token costs into account. I don't use Gemini 3.5 for coding, but I use it as something in between a search engine and agent.
    • data-ottawa 2 hours ago
      I think 3.5 flash is trying to target agentic work, like Google Search or ADK (agent development kit) use cases.

      It’s something cheap enough you’d put out in front of your customers, and Opus is expensive enough you wouldn’t.

  • fridder 1 hour ago
    I wonder if it will be better at building TUI's. It has been absolutely abysmal at interacting with them and building them
    • chatmasta 1 hour ago
      Claude can build UI but it sucks at testing it and iterating on it. Fable showed some improvements in this regard but alas.
      • Chu4eeno 35 minutes ago
        It seems to do it just fine when in desktop applications using Qt, fwiw., it leverages all the standard Qt GUI testing stuff (and if you have the money you can just integrate Squish which has LLM support now).
  • knollimar 1 hour ago
    Where is 3.5 pro?
    • squidbeak 38 minutes ago
      Google said June, and all its model updates seem to be on Tuesdays, Wednesdays or Thursdays. So unless the release is slipping, either tomorrow or Tuesday.
      • WarmWash 33 minutes ago
        Rumor is now July, although preliminary A/B tests people are getting show promise with whatever they have right now.
  • beastman82 2 hours ago
    No UI like their competitors Claude CoWork or Codex. This is vaporware
  • zuzululu 1 hour ago
    performance is quite impressive given that its 3x cheaper than 5.5
  • villgax 2 hours ago
    Will it skip Ads lol
    • humblyCrazy 2 hours ago
      I looked at their demo and it does not
      • chatmasta 1 hour ago
        Better question might be will it skip recaptcha?