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

91–100 of 175 posts

Re: Computer use in Gemini 3.5 Flash

#91

Post by jatora »

hashta wrote: post #80
smallstepforman wrote: post #60

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 interesting because my experience has been almost the opposite. A few months ago I tested Gemini on converting screenshots of tables from PDF files into CSV. I tried it on several different tables and it got every one right. It consistently outperformed ChatGPT.

anyone who has used both knows this is inaccurate or dishonestly stated (ie. you were using gpt nano or some nonsense)

Re: Computer use in Gemini 3.5 Flash

#92

Post by andrewbutts »

YuechenLi wrote: post #88

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…

Yes, Gemini CLI and Antigravity

Re: Computer use in Gemini 3.5 Flash

#93

Post by kakugawa »

YuechenLi wrote: post #88

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…

Antigravity CLI (which replaced Gemini CLI):

https://antigravity.google/product/antigravity-cli

Re: Computer use in Gemini 3.5 Flash

#95

Post by dbbk »

quantumleaper wrote: post #59
nzach wrote: post #56

Earlier quoted context omitted.

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 conver…

This doesn't require computer use, just a bash tool (and possibly fetch to get ffmpeg documentation)

Yeah even Claude Cowork would do this, doesn't need "computer use"

Re: Computer use in Gemini 3.5 Flash

#96

Post by BobbyTables2 »

smallstepforman wrote: post #60

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…

Tabula + Excel could probably do it quicker.

Re: Computer use in Gemini 3.5 Flash

#97

Post by mjcohen »

smallstepforman wrote: post #60

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…

Years ago, I used Acrobat to extract tables from a PDF. Had to do it manually, but it pasted nicely into Excel.

Re: Computer use in Gemini 3.5 Flash

#98

Post by anitil »

smallstepforman wrote: post #60

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…

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).

Re: Computer use in Gemini 3.5 Flash

#99

Post by anigbrowl »

smallstepforman wrote: post #60

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…

It's extremely hit or miss. I've had it one-shot a pretty decent analytic prototype from a brief description, but also had it get trapped in hour-long back and forth regression hell over incredibly simple things like adding a static favicon (ie it would add it, then keep taking it away with every subsequent iteration, breaking something else every time it was asked to put the favicon back etc.).

Re: Computer use in Gemini 3.5 Flash

#100

Post by janalsncm »

jgalt212 wrote: post #71
whh wrote: post #68

Earlier quoted context omitted.

Getting AI/ML to acknowledge "I don't know" is such a challenge.

Not true regarding ML, most ML methods support RMSE even if they are non parametric methods.

RMSE is just an extrapolation from the training data. If the data is wrong because the world changed, any model (parametric or not) can be confidently incorrect.
Post reply on HN