Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 2.0: our new AI model for the agentic era

blog.google

Post reply on HN
Print view View original

261–270 of 512 posts

Re: Gemini 2.0: our new AI model for the agentic era

#261

Post by menaerus »

whimsicalism wrote: post #194
rowanG077 wrote: post #166

Earlier quoted context omitted.

That makes no sense. Inference cost dwarf training cost if you have a succesfull product pretty quickly. Afaik there is no commodity hardware that can run state of the art models like chatgpt-o1.

> Afaik there is no commodity hardware that can run state of the art models like chatgpt-o1. Stack enough GPUs and any of them can run o1. Building a chip to infer LLMs is much easier than building a training chip. Just because one cost dwarfs another does not mean that this is where the most marginal value from developing a better chip will be, especially if other people are just doing it for you. Google gets a good…

Each GPU costs ~50k. You need at least 8 of them to run mid-sized models. Then you need a server to plug those GPUs into. That's not commodity hardware.

Re: Gemini 2.0: our new AI model for the agentic era

#262

Post by UltraSane »

pcwelder wrote: post #256
simonw wrote: post #113

I released a new llm-gemini plugin with support for the Gemini 2.0 Flash model, here's how to use that in the terminal: llm install -U llm-gemini llm -m gemini-2.0-flash-exp 'prompt goes here' LLM installation: https://llm.datasette.io/en/stable/setup.html Worth noting that the Gemini models have the ability to write and then execute Python code. I tried that like this: llm -m gemini-2.0-flash-exp -o code_execution 1…

Code execution is okay, but soon runs into the problem of missing packages that it can't install. Practically, sandboxing hasn't been super important for me. Running claude with mcp based shell access has been working fine for me, as long as you instruct it to use venv, temporary directory, etc.

Is there a guide on how to do that?

Re: Gemini 2.0: our new AI model for the agentic era

#263

Post by rrrrrrrrrrrryan »

CSMastermind wrote: post #173
EternalFury wrote: post #47

Think of Google as of a tanker ship. It takes a while to change course, but it has great momentum. Sundar just needs to make sure the course is right.

That's almost word for word what people said about Windows Phone when I was at Microsoft.

Windows Phone was actually great though, and would've eventually been a major player in the space if Microsoft were stubborn enough to stick with it long enough, like they did with the Xbox.

By his own admission, Gates was extremely distracted at the time by the antitrust cases in Europe, and he let the initiative die.

Re: Gemini 2.0: our new AI model for the agentic era

#264

Post by simonw »

simonw wrote: post #113

I released a new llm-gemini plugin with support for the Gemini 2.0 Flash model, here's how to use that in the terminal: llm install -U llm-gemini llm -m gemini-2.0-flash-exp 'prompt goes here' LLM installation: https://llm.datasette.io/en/stable/setup.html Worth noting that the Gemini models have the ability to write and then execute Python code. I tried that like this: llm -m gemini-2.0-flash-exp -o code_execution 1…

Published some more detailed notes on my explorations of Gemini 2.0 here https://simonwillison.net/2024/Dec/11/gemini-2/

Re: Gemini 2.0: our new AI model for the agentic era

#265

Post by msabalau »

egeozcan wrote: post #158
StableAlkyne wrote: post #152

Earlier quoted context omitted.

> Remains to be seen how well they will be able to productize and market The challenge is trust. Google is one of the leaders in AI and are home to incredibly talented developers. But they also have an incredibly bad track record of supporting their products. It's hard to justify committing developers and money to a product when there's a good chance you'll just have to pivot again once they get bored. Say what you w…

> they also have an incredibly bad track record of supporting their products Incredibly bad track record of supporting products that don't grow . I'm not saying this to defend Google, I'm still (perhaps unreasonably) angry because of Reader, it's just that there is a pattern and AI isn't likely to fit that for a long while.

Yeah, either AI is significant, in which case Google isn't going to kill it. Or AI is a bubble, in any of the alternatives one might pick can easily crash and die long before Google ends of life anything.

This isn't some minor consumer play, like a random tablet or Stadia. Anyone who has paying attention would have noticed that AI has been an important, consistent, long term strategic interest of Google's for a very long time. They've been killing off the fail/minor products to invest in this.

Re: Gemini 2.0: our new AI model for the agentic era

#267

Post by pcwelder »

UltraSane wrote: post #262
pcwelder wrote: post #256

Earlier quoted context omitted.

Code execution is okay, but soon runs into the problem of missing packages that it can't install. Practically, sandboxing hasn't been super important for me. Running claude with mcp based shell access has been working fine for me, as long as you instruct it to use venv, temporary directory, etc.

Is there a guide on how to do that?

For building mcp server? The official docs do a great job

https://modelcontextprotocol.io/introduction

My own mcp server could be an inspiration on Mac. It's based on pexpect to enable repl session and has some tricks to prevent bad commands.

https://github.com/rusiaaman/wcgw

However, I recommend creating one with your own customised prompts and tools for maximum benefit.

Re: Gemini 2.0: our new AI model for the agentic era

#268

Post by msabalau »

whimsicalism wrote: post #245
SimianSci wrote: post #225

Earlier quoted context omitted.

I think Apple is uniquely disadvantaged in the AI race to a point people dont realize. They have less training data to use, having famously been focused on privacy for its users and thus having no particular advantage in this space due to not having customer data to train on. They have little to no cloud business, and while they operate a couple of services for their users, they do not have the infrastructure scale t…

yeah i’ve never understood the outsized optimism for apple’s ai strategy, especially on hn. they’re a little bit less of a nobody than they used to be, but they’re basically a nobody when it comes to frontier research/scaling. and the best model matters way more than on-device which can always just be distilled later and find some random startup/chipco to do inference

Theory: Apple's lifestyle branding is quite important to the identity of many in the community here. I mean, look at the buy-in at launch for Apple Vision Pro by so many people on HN--it made actual Apple communities and publications look like jaded skeptics.

Re: Gemini 2.0: our new AI model for the agentic era

#269

Post by bastardoperator »

StableAlkyne wrote: post #152
crowcroft wrote: post #15

Big companies can be slow to pivot, and Google has been famously bad at getting people aligned and driving in one direction. But, once they do get moving in the right direction the can achieve things that smaller companies can't. Google has an insane amount of talent in this space, and seems to be getting the right results from that now. Remains to be seen how well they will be able to productize and market, but hard…

> Remains to be seen how well they will be able to productize and market The challenge is trust. Google is one of the leaders in AI and are home to incredibly talented developers. But they also have an incredibly bad track record of supporting their products. It's hard to justify committing developers and money to a product when there's a good chance you'll just have to pivot again once they get bored. Say what you w…

Putting your trust in Google is a fools errand. I don't know anyone that doesn't have a story.

Re: Gemini 2.0: our new AI model for the agentic era

#270

Post by nrvn »

CamperBob2 wrote: post #251
p1esk wrote: post #13

Earlier quoted context omitted.

Are these benchmarks still meaningful?

I've started keeping an eye out for original brainteasers, just for that reason. GCHQ's Christmas puzzle just came out [1], and o1-pro got 6 out of 7 of them right. It took about 20 minutes in total. I wasn't going to bother trying those because I was pretty sure it wouldn't get any of them, but decided to give it an easy one (#4) and was impressed at the CoT. Meanwhile, Google's newest 2.0 Flash model went 0 for 7.…

Did it get the 8 right? The linked article provides the wrong answer btw.
Post reply on HN