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

241–250 of 259 posts

Re: Gemini 2.5 Deep Think

#241

Post by baggachipz »

gkbrk wrote: post #235
baggachipz wrote: post #28

Earlier quoted context omitted.

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.

Sounds like you don't like a product choice that your company made. Have you considered talking to your company?

Oh yes, I'm sure they'd change their entire setup and way of doing business based on my complaint.

Re: Gemini 2.5 Deep Think

#243

Post by sunaookami »

panarky wrote: post #60
sunaookami wrote: post #51

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.

Obviously I'm not talking about API keys, this is what I would recommend though: https://ai.google.dev/gemini-api/docs/rate-limits#free-tier

I'm talking about "logging in with a Google Account".

Re: Gemini 2.5 Deep Think

#244

Post by sunaookami »

indigodaddy wrote: post #62
panarky wrote: post #60

Earlier quoted context omitted.

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?

There is no difference.

Re: Gemini 2.5 Deep Think

#245

Post by panarky »

sunaookami wrote: post #243
panarky wrote: post #60

Earlier quoted context omitted.

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.

Obviously I'm not talking about API keys, this is what I would recommend though: https://ai.google.dev/gemini-api/docs/rate-limits#free-tier I'm talking about "logging in with a Google Account".

Your link shows the free tier gets 100 Pro requests per day.

That matches my experience with a free account. With Gemini CLI it doesn't seem to matter if I log in with a Google Account or use an API key from AI Studio with billing disabled.

Yesterday I had two coding sessions in Gemini CLI with a total of 73 requests to Pro with no rate limiting.

https://imgur.com/a/Ki6g1qc

I can't explain why you're seeing something else, but my experience has been pretty consistent.

Maybe your usage pattern is different from mine and you're getting hit by the 5 RPM limit??

Re: Gemini 2.5 Deep Think

#246

Post by hirako2000 »

red75prime wrote: post #229
hirako2000 wrote: post #196

Earlier quoted context omitted.

Off the thousands of responses I have read from the top LLMs in the last couple of years: never seen one that was creative. Throwing writing, coding, problem solving, mathematical questions and what not. It's somewhat easier to perceive the creativeless aspect with stable diffusion. I'm not talking about the missing limb or extra finger glitches. With a bit of experience looking through generated images our brain eve…

An opinion on the current state of the field. The usual stochastic parrot mention. That, I see. Reasons for the existence of the wall? Not so much.

That it is usual doesn't mean it's false.

Everyone I talked to, knowledgeable in machine learning and/or deep learning, who had no reason to pretend of course, agreed an LLM is a stochastic machines. That it is couples with very good other NLP techniques doesn't change that.

It is why even the best models today miss the shot by a large margin, then hit a decent match. Again back to the creative issue. If it was done before, a good input and a well trained model on good data will output good data likely to match with the best (matching) answer ever produced. Some NLP to make it sound unique is not equal to creativity.

Re: Gemini 2.5 Deep Think

#247

Post by thunky »

h4ch1 wrote: post #239
thunky wrote: post #237

Earlier quoted context omitted.

> Even IF that were true (and I'd argue that it is NOT) Can you share what these "hard problems" are that > 1% of developers are working on?

Try using any AI tool to write a working realtime GI (global illumination) implementation. I've been working on a novel implementation for 60fps/1080p GI and everytime I use Copilot or Claude to even try fixing a minor bug/troubleshoot it nukes entire functions and rewrites them using garbled shader code, old syntax/methods. Puts things into stark perspective for me. PS. no amount of prompt engineering will save you…

> I've been working on a novel implementation for 60fps/1080p GI

I don't think this is the type of work a "normal" developer is working on though, which is what my question was targeting.

I would think 99%+ are going to use an existing implementation like unreal engine, which AI can certainly help with.

Re: Gemini 2.5 Deep Think

#248

Post by _proofs »

nusl wrote: 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.

my recent experience with flash and using it to prototype a c++ header i was developing:

- it was great to brainstorm with but it routinely introduced edits and dramatic code changes, often unnecessary and many times causing regressions to existing, tested code. - numerous times recursion got introduced to revisions without being prompted or without any justified or good reason - hallucinated a few times regarding c++ type deduction semantics

i eventually had to explicitly tell it to not introduce edits in any working code being iterated on without first discussing the changes, and then being prompted by me to introduce the edits.

all in all i found base chatgpt a lot more productive and accurate and ergonomic for iterating (on the same problem just working it in parallel with gemini).

- code changes were not always arbitrarily introduced or dramatic - it attempted to always work with the given code rather than extrapolate and mind read - hallucinated on some things but quickly corrected and moved forward - was a lot more interactive and documenting - almost always prompted me first before introducing a change (after providing annotated snippets and documentation as the basis for a proposed change or fix)

however, both were great tools to work with when it came to cleaning up or debugging existing code, especially unit testing or anything related to TDD

Re: Gemini 2.5 Deep Think

#249

Post by littlestymaar »

zozbot234 wrote: post #106
littlestymaar wrote: post #37

Earlier quoted context omitted.

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).

> 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 I don't think this is correct, especially given MoE. You can save some memory bandwidth by reusing model parameters, but that's about it. It's not giving you the same speed as a single query.

Absolutely, it's not going to work that well for MoE, though today most local models (except Qwen3-30B-A3B) are dense ones.

But even for MoE it will still work: sure the second parallel agent running is going to divide the token rate by almost two, but the reduction is exponentially decreasing and the 30th will almost be free. So if you have enough VRAM to run Qwen3-32B, you can run Qwen3-30B-3A at the same speed as the 32B version but you'll be running a hundred of instances.

Re: Gemini 2.5 Deep Think

#250

Post by dataviz1000 »

zyngaro wrote: post #236
dataviz1000 wrote: post #81

Earlier quoted context omitted.

Several years ago I thought a good litmus test for mastery of coding is not finding a solution using internet search nor getting well written questions about esoteric coding problems answered on StackOverflow. For a while, I would post a question and answer my own question after I solved the problem for posterity (or AI bots). I always loved getting the "I've been working on this for 3 days and you saved my life" com…

Curious to know what are those challenging programming problems are. Can you share some examples?

Currently I'm porting the Playwright / Puppeteer client API to run in a Chrome extension without using the Chrome DevTools Protocol (CDP). Since there is 100s of Chrome extension AI copilots using Playwright with CDP with all the problems that come with that, I believe my library can be very useful. The vscode copilot chat with any model is always trying to evaluate strings in the content script using chrome.scripting.executeScript with eval('') and new Function('') which violates the CSP policy in MV3. The use case is novel but calling executeScript is common and this policy has been enforced for the last 2.5 years and available for a couple before that. Worse is it will convert my valid function definitions to eval() and new Function('') even though it has nothing to do with prompt.
Post reply on HN