Live data from Hacker News

Gemini 2.5 Deep Think

blog.google

61–70 of 259 posts

Re: Gemini 2.5 Deep Think

#61

Ladies and Gentlemen, Here's Gemini Deep Think when prompted with: "Create a svg of a pelican riding on a bicycle" https://www.svgviewer.dev/s/5R5iTexQ Beat Simon Willison to it :)

Meme benchmarks like this and Strawberry are funny but very easy to game, I bet they're all over training sets nowadays.

Re: Gemini 2.5 Deep Think

#62
post #60

Earlier quoted context omitted.

It doesn't, it's not "1000 Gemini Pro" requests for free, Google misled everyone. It's 1000 Gemini requests, Flash included. You get like 5-7 Gemini Pro requests before you get limited.

I'm getting 100 Gemini Pro requests per day with an AI Studio API key that doesn't have billing enabled. After that it's bumped down to Flash, which is surpisingly effective in Gemini CLI. If I need Pro, I just swap in an API from an account with billing enabled, but usually 100 requests is enough for a day of work.

I created an AI Studio key (unbilled) probably over a year ago or so. Is it still good for the current models are should I be creating a new key?

Re: Gemini 2.5 Deep Think

#63
post #57

Been using Gemini for a few months, somehow it's gotten much, much worse in that time. Hallucinations are very common, and it will argue with you when you point it out. So, don't have much confidence.

In my experience with chat, Flash has gotten much, much better. It's my go-to model even though I'm paying for Pro.

Pro is frustrating because it too often won't search to find current information, and just gives stale results from before its training cutoff. Flash doesn't do this much anymore.

For coding I use Pro in Gemini CLI. It is amazing at coding, but I'm actually using it more to write design docs, decomp multi-week assignments down to daily and hourly tasks, and then feed those docs back to Gemini CLI to have it work through each task sequentially.

With a little structure like this, it can basically write its own context.

Re: Gemini 2.5 Deep Think

#64
Upgraded and quickly hit my limit. And find that they have limits, I just wish that they were more transparent. Even if it's just a vague statement about limited usage. I assumed it would be similar to regular Gemini 2.5 on the pro plan but it's not

Re: Gemini 2.5 Deep Think

#66
post #57

Been using Gemini for a few months, somehow it's gotten much, much worse in that time. Hallucinations are very common, and it will argue with you when you point it out. So, don't have much confidence.

I feel the same, but cannot measure the effect in any context benchmark like fiction.livebench.

Are they aggressively quantizing, or are our expectations silently increasing ?

Re: Gemini 2.5 Deep Think

#67

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 could be that your problem was too simple to justify the use of Deep Think.

But yes, Google should have figured that out and used a less expensive mode of reasoning.

Re: Gemini 2.5 Deep Think

#68

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-conso…

I am not seeing this llm serve command

Re: Gemini 2.5 Deep Think

#69

Ladies and Gentlemen, Here's Gemini Deep Think when prompted with: "Create a svg of a pelican riding on a bicycle" https://www.svgviewer.dev/s/5R5iTexQ Beat Simon Willison to it :)

Can it do circuit diagrams? Because that's one practical area where I think the AI models are lacking.

Re: Gemini 2.5 Deep Think

#70

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-conso…

Is the European Union a consortium of consortiums?
Post reply on HN