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

Gemini 2.5 Deep Think

blog.google

Post reply on HN
Print view View original

31–40 of 259 posts

Re: Gemini 2.5 Deep Think

#31

Post by serialNumber »

baggachipz wrote: post #28
serialNumber wrote: post #25

Earlier quoted context omitted.

I’m never the one to defend AI, but what do you mean? Is it the “AI overview” that pops up on Google? Other than that, I would say Gemini is definitely less in your face than ChatGPT for example

My company uses google workspace and every google doc, spreadsheet, calendar, online meeting and search puts nonstop callouts and messages about using Gemini. It's gotten so bad that I'm about to try building a browser extension to block that bullshit. It clutters the UI and nags. If I wanted that crap, I'd turn it on.

I see - I feel the same way about Copilot (as my company uses the Microsoft ecosystem).

Re: Gemini 2.5 Deep Think

#32

Post by satvikpendem »

mvieira38 wrote: post #22
highfrequency wrote: post #3

Approach is analogous to Grok 4 Heavy: use multiple "reasoning" agents in parallel and then compare answers before coming back with a single response, taking ~30 minutes. Great results, though it would be more fair for the benchmark comparisons to be against Grok 4 Heavy rather than Grok 4 (the fast, single-agent model).

Is o3-pro the same as these?

No, it doesn't take 30 minutes

Re: Gemini 2.5 Deep Think

#33

Post by Workaccount2 »

resoluteteeth wrote: post #17

> If you’re a Google AI Ultra subscriber, you can use Deep Think in the Gemini app today with a fixed set of prompts a day by toggling “Deep Think” in the prompt bar when selecting 2.5 Pro in the model drop down. If fixed set means fixed number it would be nice to know how many. Otherwise i would like to know what fixed set means here.

You get 10 requests per day it seems.

Apparently the model will think for 30+ minutes on a given prompt. So it seems it's more for research or dense multi-faceted problems than for general coding or writing fan fic.

Re: Gemini 2.5 Deep Think

#34

Post by foundry27 »

I started doing some experimentation with this new Deep Think agent, and after five prompts I reached my daily usage limit. For $250 USD/mo that’s what you’ll be getting folks.

It’s just bizarrely uncompetitive with o3-pro and Grok 4 Heavy. Anecdotally (from my experience) this was the one feature that enthusiasts in the AI community were interested in to justify the exorbitant price of Google’s Ultra subscription. I find it astonishing that the same company providing free usage of their top models to everybody via AI Studio is nickel-and-diming their actual customers like that.

Performance-wise. So far, I couldn’t even tell. I provided it with a challenging organizational problem that my business was facing, with the relevant context, and it proposed a lucid and well-thought-out solution that was consistent with our internal discussions on the matter. But o3 came to an equally effective conclusion for a fraction of the cost, even if it was less “cohesive” of a report. I guess I’ll have to wait until tomorrow to learn more.

Re: Gemini 2.5 Deep Think

#35

Post by xnx »

lynx97 wrote: post #6

Wait... So if someone cool enough, they could actually give us a DeepThought model? Please, let that happen. Vendor-DeepThought-42B maybe?

> could actually give us a DeepThought model

Yes, but the response time is terrible. 7.5 million years

Re: Gemini 2.5 Deep Think

#36

Post by TheAceOfHearts »

I would be interested in reading about how people who are paying for access to Google's top AI plan are intending to use this. Do you have any examples of immediate use-cases that might benefit?

Is Google using this tool internally? One would expect them to give some examples of how it's helping internal teams accelerate or solve more challenging problems, if they were eating their own dogfood.

Re: Gemini 2.5 Deep Think

#37

Post by littlestymaar »

highfrequency wrote: post #3

Approach is analogous to Grok 4 Heavy: use multiple "reasoning" agents in parallel and then compare answers before coming back with a single response, taking ~30 minutes. Great results, though it would be more fair for the benchmark comparisons to be against Grok 4 Heavy rather than Grok 4 (the fast, single-agent model).

That this kind of approach works is good news for local LLM enthusiasts, as it makes Cloud LLM using this more expensive while local LLM can do so for free up to a point (because LLM inference is limited by memory bandwidth not compute, you can run multiple queries in parallel on your graphic card at the same speed as the single one. Until you become compute-bound of course).

Re: Gemini 2.5 Deep Think

#38

Post by andsoitis »

foundry27 wrote: post #34

I started doing some experimentation with this new Deep Think agent, and after five prompts I reached my daily usage limit. For $250 USD/mo that’s what you’ll be getting folks. It’s just bizarrely uncompetitive with o3-pro and Grok 4 Heavy. Anecdotally (from my experience) this was the one feature that enthusiasts in the AI community were interested in to justify the exorbitant price of Google’s Ultra subscription. I…

it turns out that AI at this level is very expensive to run (capex, energy). my bet is that AI itself won't figure out how to overcome these constraints and reach escape velocity.

Re: Gemini 2.5 Deep Think

#39

Post by raincole »

foundry27 wrote: post #34

I started doing some experimentation with this new Deep Think agent, and after five prompts I reached my daily usage limit. For $250 USD/mo that’s what you’ll be getting folks. It’s just bizarrely uncompetitive with o3-pro and Grok 4 Heavy. Anecdotally (from my experience) this was the one feature that enthusiasts in the AI community were interested in to justify the exorbitant price of Google’s Ultra subscription. I…

Interestingly Gemini CLI has a very generous free quota. Is Google's strategy just overpricing some stuff and subsidizing the underpriced stuff?

Re: Gemini 2.5 Deep Think

#40

Post by irthomasthomas »

You can spin up a version of this at home using simonw's LLM cli with the llm-consortium plugin.

Bonus 1: Use any combination of models. Mix n match models from any lab.

Bonus 2: Serve your custom consortium on a local API from a single command using the llm-model-gateway plugin and use it in your apps and coding assistants.

https://x.com/karpathy/status/1870692546969735361

  > uv tool install llm
  llm install llm-consortium
  llm consortium save gthink-n5       -m gemini-pro -n 5 --arbiter gemini-flash --confidence-threshold 99 --max-iterations 4

  llm serve --host 0.0.0.0

  curl http://0.0.0.0:8000/v1/chat/completions \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gthink-n5",
    "messages": [{"role": "user", "content": "find a polynomial algorithm for graph-isomorphism"}]
  }'
You can also build a consortium of consortiums like so:

  llm consortium save gem-squared -m gthink-n5 -n 2 --arbiter gem-flash
Or even make the arbiter a consortium:

  llm consortium save gem-cubed -m gthink-n5 -n 2 --arbiter gthink-n5 --max-iteration 2
or go openweights only:

  llm consortium save open-council -m qwen3:2 -m kimi-k2:2 -m glm-4.5:2 -m mistral:2 --arbiter minimax-m1 --min-iterations 2 --confidence-threshold 95
https://GitHub.com/irthomasthomas/llm-consortium
Post reply on HN