In the last weeks I experimented with Claude Computer Use to automate some daily tasks (via its Ui.Vision chat integration, see https://forum.ui.vision/t/v9-5-0-brings-computer-use-ai-chat... ) - and the results are mixed. Claude gets things wrong way too often to be useful.
Has anyone done any comparison Claude Computer Use vs OpenAI Operator? Is it signifcantly better?
100% this. I am using the open source Ui.vision to automate some business tasks. Works well, but only 10% of the work is for automating the main workflow, 90% of the work goes into error and edge case handling (e. g. Internet down, website (to scrape data from) down, some input data has typos or the wrong date format, etc).
A human can work around all these error cases once she encounters them. Current RPA tools like Uipath or ui.vision need explicit programming for every potential situation. And I see no indication that Claude is doing any better than this.
For starters, for visual automation to work reliably the OCR quality needs to improve further and be 100% reliable. Even in that very basic "AI" area, Claude, ChatGPT, Gemini are good, but not good enough yet.
Totally disagree. Just one example: Tesla has only two global mass market models (3+Y). There is plenty of room to innovate on this topic alone. Model 2? Model whatever. Nothing new in years.
Wow, what a click-baity misleading headline. Key point is that this number is going down:
"The big news is that more and more people are opting to trade their Teslas for an EV from a legacy automaker"
This might be me in a few years. Tesla stopped being innovative years ago. No surprise, its CEO is high on drugs most of the time and spends his days (and nights) posting childish memes.
What you said is all correct, but there are some positive steps as well, for example ELLIS: https://ellis.eu/
ELLIS is a great way to compete with the top US universities. Much more is needed, especially access to computing power, just as the CERN for AI proposal suggests.
> and debug if it errors or isn't what you wanted.
That is a potential problem Because at this point the user will still need good HTML/Selenium/coding knowledge to debug. We ran into the same issue using chatgpt generated scripts for ui.vision. Once a QA person has to figure out why some generated code does not work, it becomes a hassle and removes any initial advantage over the classic record & replay approach.
> BEVs are improving quickly so what I buy might be superseded soon
That WAS my concern, but EV resale value is amazingly stable, better than most ICE in my area (EU). After all, EVs are still cars, so innovation cycles are long (many years).
Exactly this. I tried so hard to like it (since I paid for it), but I have found 0 good uses cases for it.
I would assume that macOS sends at least some basic usage data for the touch bar back to Apple HQ. I wonder how often it is actually used... and I would love the hear the responsible product manager defend it.
A solution to run non-headless Chrome browsers in the cloud would be welcome. We used Sikuli and now UI.Vision RPA for test automation, and have to manage the servers for it ourself. If I could outsource this to a service like browserless, it would be convenient. (Applitools was an option I looked at)
The web app we are testing right now (SaaS for architects) makes heavy use of canvas elements and can't be tested headless.
Has anyone done any comparison Claude Computer Use vs OpenAI Operator? Is it signifcantly better?