I feel like screenshots should be the last thing you reach for. There's a whole universe of data from accessibility subsystems.
Gemini 2.5 Computer Use model
21–30 of 339 posts
Re: Gemini 2.5 Computer Use model
#22My general experience has been that Gemini is pretty bad at tool calling. The recent Gemini 2.5 Flash release actually fixed some of those issues but this one is Gemini 2.5 Pro with no indication about tool calling improvements.
Re: Gemini 2.5 Computer Use model
#23doesn't seem like it makes sense to train AI around human user interfaces which aren't really efficient. It is like building a mechanical horse.
We're training natural language models to reason by emulating reasoning in natural language, so it's very on brand.
Re: Gemini 2.5 Computer Use model
#24Have average Google developers been told/hinted that their bonuses/promotions will be tied to their proactivity in using Gemini for project work?
I know there was a memo telling Googlers they are expected to use AI at work and it’s expected for their performance to increase as a result.
The HBO's Silicon Valley ended way too soon. The plot pretty much writes itself.
Re: Gemini 2.5 Computer Use model
#25It successfully got through the captcha at https://www.google.com/recaptcha/api2/demo
The automation is powered through Browserbase, which has a captcha solver. (Whether it is automated or human, I don't know.)
Re: Gemini 2.5 Computer Use model
#26doesn't seem like it makes sense to train AI around human user interfaces which aren't really efficient. It is like building a mechanical horse.
In my country there's a multi-airline API for booking plane tickets, but the cheapest of economy carriers only accept bookings directly on their websites.
If you want to make something that can book every airline? Better be able to navigate a website.
Re: Gemini 2.5 Computer Use model
#27doesn't seem like it makes sense to train AI around human user interfaces which aren't really efficient. It is like building a mechanical horse.
This is just like the comments suggesting we need sensors and signs specifically for self-driving cars for them to work.
It'll never happen, so companies need to deal with the reality we have.
Re: Gemini 2.5 Computer Use model
#28doesn't seem like it makes sense to train AI around human user interfaces which aren't really efficient. It is like building a mechanical horse.
Why do you think we have fully self driving cars instead of just more simplistic beacon systems? Why doesn't McDonald's have a fully automated kitchen?
New technology is slow due to risk aversion, it's very rare for people to just tear up what they already have to re-implement new technology from the ground up. We always have to shoe-horn new technology into old systems to prove it first.
There are just so many factors that get solved by working with what already exists.
Re: Gemini 2.5 Computer Use model
#29Painfully slow
Re: Gemini 2.5 Computer Use model
#30It successfully got through the captcha at https://www.google.com/recaptcha/api2/demo
Post edited: I was wrong about this. Gemini tried to solve the Google CAPTCHA but it was actually Browserbase that did the solve, notes here: https://simonwillison.net/2025/Oct/7/gemini-25-computer-use-...