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

421–430 of 512 posts

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

#421

Post by sippeangelo »

jncfhnb wrote: post #16

Am I alone in thinking the word “agentic” is dumb as shit? Most of these things seem to just be a system prompt and a tool that get invoked as part of a pipeline. They’re hardly “agents”. They’re modules.

Aside from sounding "dumb as shit", I also think it's the completely wrong abstraction. Every time I've split up work between multiple specialized LLM "agents", they've done an WAY worse job than one monolith LLM that had access to all the tools it needs and can "reason" about the whole task.

All the common tricks, like creating a list of steps that are then executed by specialized agents in order, for example, fall flat as soon as one agent returns a result that contradicts the initial steps. It's simply a bandaid for short context sizes and LLMs that can't remain focused past the first few thousand tokens of prompt.

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

#422

Post by mike_hearn »

dagmx wrote: post #358
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…

There’s an easy solution here: Apple isn’t trying to compete with the big models everyone else is running. They’re betting in the opposite direction that many small models is a better value ad for their customers. And they can call out to other services as needed for the larger stuff. I’m in the camp that this is the right call for consumers, instead of trying to compete on the large model side. They’ve yet to delive…

Apple have trained their own foundation LLM.

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

#423

Post by nrvn »

CamperBob2 wrote: post #324
nrvn wrote: post #270

Earlier quoted context omitted.

Did it get the 8 right? The linked article provides the wrong answer btw.

I didn't see a straightforward way to submit the final problem, because I used different contexts for each of the 7 subproblems. Given the right prompt, though, I'm sure it could handle the 'find the corresponding letter from the landmarks to form an anagram' part. That's easier than most of the other problems. You're saying the ultimate answer isn't 'PROTECTING THE UNITED KINGDOM'?

if you follow the sleigh morse path starting from the robin it will be 'united in protecting the kingdom'.

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

#425

Post by kranke155 »

bloomingkales wrote: post #116
panabee wrote: post #86

Earlier quoted context omitted.

With many research areas converging to comparable levels, the most critical piece is arguably vertical integration and forgoing the Nvidia tax. They haven't wielded this advantage as powerfully as possible, but changes here could signal how committed they are to slaying the search cash cow. Nadella deservedly earned acclaim for transitioning Microsoft from the Windows era to cloud and mobile. It will be far more impr…

They have to not get blind sided by Sora, while at the same time fighting the cloud war against MS/Amazon. Weirdly Google is THE AI play. If AI is not set to change everything and truly is a hype cycle, then Google stock withstands and grows. If AI is the real deal, then Google still withstands due to how much bigger the pie will get.

Sora is a toy. No understanding of physics. Fairly expensive. Hard to tell stories with it. I work in video production. The industry is not big enough for you to invest billions and billions into. It’s currently in a total state of crisis.

Video production is just not big enough of a market to make a difference in the AI race. I don’t understand why any AI company would spend significant amount of resources matching Sora when I don’t really think it will be a 10 billion dollar product (yet).

Plus Google is well positioned to match it anyway, since they have YouTube data they can probably license to their AI gen video training.

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

#426

Post by ErikBjare »

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.

This is why I started building gptme almost 2 years ago. Making these agents/tools local-first has many benefits like that.

GitHub: https://github.com/ErikBjare/gptme

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

#427

Post by slowmovintarget »

modeless wrote: post #383

https://aistudio.google.com/live is by far the coolest thing here. You can just go there and share your screen or camera and have a running live voice conversation with Gemini about anything you're looking at. As much as you want, for free. I just tried having it teach me how to use Blender. It seems like it could actually be super helpful for beginners, as it has decent knowledge of the toolbars and keyboard shortcu…

At least you can theoretically stop sharing with this one. Microsoft was essentially trying to do this, but doing it for everything on your PC, with zero transparency.

Here's Google doing essentially the same thing, even more so that it's explicitly shipping your activity to the cloud, and this response is so different from the "we're sticking this on your machine and you can't turn it off" version Microsoft was attempting to land. This is what Microsoft should have done.

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

#428

Post by IanCal »

computergert wrote: post #372

It's funny how even the latest AI models struggle with simple questions. "What's the first name of Freddy LaStrange"? >> "I do not have enough information about that person to help with your request. I am a large language model, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions, but my knowledge about this person is limited. Is there anything else I can do…

These kinds of things just strike me as trick questions, why would anyone ask that?

Also

> Freddy LaStrange is a fictional character and his first name is Freddy.

and

> Freddy is a nickname for Frederick. So, the first name of Freddy LaStrange is Frederick.

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

#429

Post by Huppie »

sky2224 wrote: post #397
modeless wrote: post #383

https://aistudio.google.com/live is by far the coolest thing here. You can just go there and share your screen or camera and have a running live voice conversation with Gemini about anything you're looking at. As much as you want, for free. I just tried having it teach me how to use Blender. It seems like it could actually be super helpful for beginners, as it has decent knowledge of the toolbars and keyboard shortcu…

THIS is the thing I'm excited for with AI. I'm someone that becomes about 5x more productive when I have a person watching or just checking in on me (even if they're just hovering there). Having AI to basically be that "parent" to kick me into gear would be so helpful. 90% of the time my problems are because I need someone to help keep the gears turning for me, but there isn't always someone available. This has the p…

Just as an FYI: I recently learned (here on HN) that this is called Body Doubling[0] there's some services around (there's at least one by someone that hangs around here) that can do this too.

[0] https://en.m.wikipedia.org/wiki/Body_doubling

Post reply on HN