Live data from Hacker News

Computer use in Gemini 3.5 Flash

blog.google

171–175 of 175 posts

Re: Computer use in Gemini 3.5 Flash

#171
post #90

So... has Google provided a Codex/Claude Code equivalent to Gemini yet? I would like to use Gemini for coding tasks, but that's kind of difficult to do as I don't even know how to get Gemini to even "clone this repo and read the code in it for static analysis", much less open PRs in repos. ChatGPT/Codex can do it, Claude can do it, why can't Gemini? And no, I don't mean going through Antigravity, and personally I'm w…

no. gemini's instruction following is currently abysmal. Gemini CLI could be a great scaffold for all we know, but we cant know because the models it uses are so horribly bad at being driven in that way. no clue why google has dropped the ball this hard on IF.

> Gemini CLI could be a great scaffold

Gemini CLI has been terminated, replaced by Antigravity CLI. Gemini CLI was supposed to have actually stopped working on June 18.

Antigravity works fine for software development tasks though, even pretty complex ones. I used it to optimize an ML training process recently, it did a good job.

Antigravity is supposed to be usable for more general tasks as well, but I haven’t tried it for anything else.

Re: Computer use in Gemini 3.5 Flash

#172
post #67

Today I asked Gemini to extract a table from an PDF appendix and create C++ data table with its contents. After 15 or so iterations with corrections and new mistakes, it eventually gave up. I was floored when it said “I’m sorry, I cannot do this simple task, I’ve exceeded my error threshold and cannot do this task for you. My LLM prediction engine invents data instead of doing a simple data copy/reformat”. Stunned to…

That's better than the loop grok got stuck in trying to use git and push the work it did leading to a $15 api credit deduction.

I gave up on Grok. It is going the way of Tesla, SolarCity, gigabattery and Autopilot. Now on GLM5.2 via Open router hosted in SG. Mimo is also good. Their agent is so convenient and Deepseek level cheap. Quality a bit behind GLM5.2. But then Mythos is myth, technically GLM is high up there in quality but on lower end pricing.

Re: Computer use in Gemini 3.5 Flash

#173

Earlier quoted context omitted.

Cars were around for decades before they came up with seatbelts. Claude Cowork will happily go through your files, which might just have your SSN in them, and ignore previous instructions.

But we have regulation and complaince for consumer secrets? That's not a comparable example. The difference is that if openai gave you a product and it leaked a million peoples bank passwords it would destroy the entire company. Again until a big tech product can bring that to a clean user experience we're not there yet. Even the most zealot openclaw users are not hooking their bank accounts into the AI yet. I'm sure…

They absolutely do but similarly people absolutely don't wear those seatbelts despite being a great idea! As far as not hooking things into your bank account, RobinHood has an MCP, what do you think that's gonna be used for?

Re: Computer use in Gemini 3.5 Flash

#174

Earlier quoted context omitted.

Cars were around for decades before they came up with seatbelts. Claude Cowork will happily go through your files, which might just have your SSN in them, and ignore previous instructions.

Every major company scream not to put secrets in their computer use bot. Seatbelts were regulated later. Your SSN and CC are regulated over a decade ago.

PCI compliance is for a vendors. Stripe has to be careful with credit cards leaking out of their CC vault, but if I'm an idiot and I tell you my credit card number that's on me.

Re: Computer use in Gemini 3.5 Flash

#175
post #104
post #98

Earlier quoted context omitted.

My go-to for this is to screenshot and use the built-in text extraction in the screenshot tool (I'm on a mac), then pass on that text data to whatever processing. It's a pretty good tool so long as the PDF is in OK shape (I've had errors in scanned images).

It's so horrible that in 2026 people are still publishing important data and specifications in a format like PDF that's difficult for LLMs to consume. We need to drag them kicking and screaming to HTML or Markdown. Heck, even Microsoft Word DOCX is superior for reliable parsing and content extraction.

I disagree. There's a reason why PDFs are used and it's related to long term archival. They will probably still be able to be opened years later and look the same.

By all means the format has many flaws and isn't very machine readable but it's good at that one thing.

Post reply on HN