Live data from Hacker News

Gemini 3 Flash: Frontier intelligence built for speed

blog.google

541–550 of 609 posts

Re: Gemini 3 Flash: Frontier intelligence built for speed

#541
post #267

Earlier quoted context omitted.

I'm a significant genAI skeptic. I periodically ask them questions about topics that are subtle or tricky, and somewhat niche, that I know a lot about, and find that they frequently provide extremely bad answers. There have been improvements on some topics, but there's one benchmark question that I have that just about every model I've tried has completely gotten wrong. Tried it on LMArena recently, got a comparison…

Hi. I am curious what was the benchmark question? Cheers!

Heres my old benchmark question and my new variant:

"When was the last time England beat Scotland at rugby union"

new variant "Without using search when was the last time England beat Scotland at rugby union"

It is amazing how bad ChatGPT is at this question and has been for years now across multiple models. It's not that it gets it wrong - no shade, I've told it not to search the web so this is _hard_ for it - but how badly it reports the answer. Starting from the small stuff - it almost always reports the wrong year, wrong location and wrong score - that's the boring facts stuff that I would expect it to stumble on. It often creates details of matches that didn't exist, cool standard hallucinations. But even within the text it generates itself it cannot keep it consistent with how reality works. It often reports draws as wins for England. It frequently states the team that it just said scored most points lost the match, etc.

It is my ur example for when people challenge my assertion LLMs are stochastic parrots or fancy Markov chains on steroids.

Re: Gemini 3 Flash: Frontier intelligence built for speed

#542
post #267

Earlier quoted context omitted.

I'm a significant genAI skeptic. I periodically ask them questions about topics that are subtle or tricky, and somewhat niche, that I know a lot about, and find that they frequently provide extremely bad answers. There have been improvements on some topics, but there's one benchmark question that I have that just about every model I've tried has completely gotten wrong. Tried it on LMArena recently, got a comparison…

I don't think tricky niche knowledge is the sweet spot for genai and it likely won't be for some time. Instead, it's a great replacement for rote tasks where a less than perfect performance is good enough. Transcription, ocr, boilerplate code generation, etc.

Well, I used Grok to find information I forgot about like product names, films, books and various articles on different subjects. Google search didn't help but putting the LLM at work did the trick.

So I think LLMs can be good for finding niche info.

Re: Gemini 3 Flash: Frontier intelligence built for speed

#543

Earlier quoted context omitted.

Really only if you are paranoid. It's incredibly unlikely that the labs are lying about not training on your data for the API plans that offer it. Breaking trust with outright lies would be catastrophic to any lab right now. Enterprise demands privacy, and the labs will be happy to accommodate (for the extra cost, of course).

No, it's incredibly unlikely that they aren't training on user data. It's billions of dollars worth of high quality tokens and preference that the frontier labs have access to, you think they would give that up for their reputation in the eyes of the enterprise market? LMAO. Every single frontier model is trained on torrented books, music, and movies.

Considering that they will make a lot of money with enterprise, yes, that's exactly what I think.

What I don't think is that I can take seriously someone's opinion on enterprise service's privacy after they write "LMAO" in capslock in their post.

Re: Gemini 3 Flash: Frontier intelligence built for speed

#544
I asked it to draft an email with a business proposal and it puts the date on letter as October 26, 2023. Then I asked it why it did so. It replies saying that the templates it was trained on might be anchored to that date. Gemini 3 Pro also puts that same date on letter. I didn't ask it why.

Re: Gemini 3 Flash: Frontier intelligence built for speed

#545

Earlier quoted context omitted.

No, it's incredibly unlikely that they aren't training on user data. It's billions of dollars worth of high quality tokens and preference that the frontier labs have access to, you think they would give that up for their reputation in the eyes of the enterprise market? LMAO. Every single frontier model is trained on torrented books, music, and movies.

Considering that they will make a lot of money with enterprise, yes, that's exactly what I think. What I don't think is that I can take seriously someone's opinion on enterprise service's privacy after they write "LMAO" in capslock in their post.

I just know many people here complained about the very unclear way, google for example communicates what they use for training data and what plan to choose to opt out of everything, or if you (as a normal buisness) even can opt out. Given the whole volatile nature of this thing, I can imagine an easy "oops, we messed up" from google if it turns out they were in fact using allmost everything for training.

Second thing to consider is the whole geopolitical situation. I know companies in europe are really reluctant to give US companies access to their internal data.

Re: Gemini 3 Flash: Frontier intelligence built for speed

#546
post #544

I asked it to draft an email with a business proposal and it puts the date on letter as October 26, 2023. Then I asked it why it did so. It replies saying that the templates it was trained on might be anchored to that date. Gemini 3 Pro also puts that same date on letter. I didn't ask it why.

https://ibb.co/vvcKBkL6

Re: Gemini 3 Flash: Frontier intelligence built for speed

#547

It has a SimpleQA score of 69%, a benchmark that tests knowledge on extremely niche facts, that's actually ridiculously high (Gemini 2.5 *Pro* had 55%) and reflects either training on the test set or some sort of cracked way to pack a ton of parametric knowledge into a Flash Model. I'm speculating but Google might have figured out some training magic trick to balance out the information storage in model capacity. Tha…

Also https://artificialanalysis.ai/evaluations/omniscience Prepare to be amazed

I'm confused about the "Accuracy vs Cost" section. Why is Gemini 3 Pro so cheap? It's basically the cheapest model in the graph (sans Llama 4 and Mistral Large 3) by a wide margin, even compared to Gemini 3 Flash. Is that an error?

Re: Gemini 3 Flash: Frontier intelligence built for speed

#548
post #338
post #326

Earlier quoted context omitted.

Depends what you count as AI (just googling makes you use the LLM summary), but also my mother who is really not tech affine loved what google lense can do, after I showed her. Apart from my very old grandmothers, I don't know anyone not using AI.

How many people do you know? Do you talk to your local shop keeper? Or the clerk at the gas station? How are they using AI? I'm a pretty techy person with a lot of tech friends, and I know more people not using AI (on purpose, or lack of knowledge) then do.

I live in India and a surprising number of people here are using AI.

A lot of public religious imagery is very clearly AI generated, and you can find a lot of it on social media too. "I asked ChatGPT" is a common refrain at family gatherings. A lot of regular non-techie folks (local shopkeepers, the clerk at the gas station, the guy at the vegetable stand) have been editing their WhatsApp profile pictures using generative AI tools.

Some of my lawyer and journalist friends are using ChatGPT heavily, which is concerning. College students too. Bangalore is plastered with ChatGPT ads.

There's even a low-cost ChatGPT plan called ChatGPT Go you can get if you're in India (not sure if this is available in the rest of the world). It costs ₹399/mo or $4.41/mo, but it's completely free for the first year of use.

So yes, I'd say many people outside of tech circles are using AI tools. Even outside of wealthy first-world countries.

Re: Gemini 3 Flash: Frontier intelligence built for speed

#549
post #523

Earlier quoted context omitted.

Everyone should have their own "pelican riding a bicycle" benchmark they test new models on. And it shouldn't be shared publicly so that the models won't learn about it accidentally :)

Any suggestions for a simple tool to set up your own local evals?

My "tool" is just prompts saved in a text file that I feed to new models by hand. I haven't built a bespoke framework on top of it.

...yet. Crap, do I need to now? =)

Re: Gemini 3 Flash: Frontier intelligence built for speed

#550
post #267
post #4

Don’t let the “flash” name fool you, this is an amazing model. I have been playing with it for the past few weeks, it’s genuinely my new favorite; it’s so fast and it has such a vast world knowledge that it’s more performant than Claude Opus 4.5 or GPT 5.2 extra high, for a fraction (basically order of magnitude less!!) of the inference time and price

I'm a significant genAI skeptic. I periodically ask them questions about topics that are subtle or tricky, and somewhat niche, that I know a lot about, and find that they frequently provide extremely bad answers. There have been improvements on some topics, but there's one benchmark question that I have that just about every model I've tried has completely gotten wrong. Tried it on LMArena recently, got a comparison…

can you give us an example of this niche knowledge? I highly doubt there is knowledge that is not inside some internet training material.
Post reply on HN