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

Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

blog.google

Post reply on HN
Print view View original

431–440 of 616 posts

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#431

Post by cherryteastain »

scrollop wrote: post #380
ngrilly wrote: post #119

Earlier quoted context omitted.

Also a big proponent of Google and Gemini, but their stubbornness in artificially splitting their consumer and enterprise products is extremely annoying. It's pretty weird that I have access to more powerful tools when using my personal Google account compared to my corporate Google Workspace account.

Apparently you cannot turn off using your data as training data with gemini. This is in line with Google's general privacy policies and it's seeming need to create a stasi file on every human.

You can turn it off but it's an all or nothing switch, if you turn it off everything will basically become a temporary chat and all past chats are deleted

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#432

Post by refulgentis »

adventured wrote: post #398
janalsncm wrote: post #295

Earlier quoted context omitted.

That and/or the business case isn’t as clear when serving enormous models? You’re constantly stuck in a red queen’s race where your profitability window is increasingly measured in weeks because the Chinese are right behind you. For small models (which are probably distilled from their big ones) you can serve them economically all the time and not hemorrhage money.

[flagged]

You’re absolutely right and it’s heartening to see. I maintain a client with ~every provider you can think of and llama.cpp and it was really tiring the last few days to see people laundering other stuff through Kimi and Qwen. They’re not even open yet, the hype was based on their own blog posts, no one’s actually running these locally, the Qwen Max’s have never been open, Kimi’s API was 1/2 the speed the benchmarks was based on, when it was up, and had 60% downtime before they had to stop accepting new accounts, and their EULAs are “your inputs and outputs are ours.” May being clear-eyed benefit us both in the long run.

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#433

Post by anthonypasq »

deltaqueue wrote: post #364
awongh wrote: post #193

Earlier quoted context omitted.

It seems like there are some credible rumors that Google is actually winning in terms of actually building models that work and don't lose money- between how they're able to price them, the TPU advantage and their capex advantage (being able to raise debt + just having a lot of cash - well I said not lose money... more like not go bankrupt). From the outside they look like they're behind in terms of frontier models,…

That "TPU advantage" might be slowing Google down (though likely not as much as their internal bureaucracy). Porting CUDA-based research, debugging, and overall experimentation speed is likely slower. The GPU is still king for training.

lmao, you know all Anthropic models are trained on TPU right?

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#435

Post by scottyah »

dTal wrote: post #358
awongh wrote: post #193

Earlier quoted context omitted.

It seems like there are some credible rumors that Google is actually winning in terms of actually building models that work and don't lose money- between how they're able to price them, the TPU advantage and their capex advantage (being able to raise debt + just having a lot of cash - well I said not lose money... more like not go bankrupt). From the outside they look like they're behind in terms of frontier models,…

In terms of open models, Gemma 4 beats the pants off everything else to the point that paying for APIs becomes hard to justify. Qwen has the meme-share for coding, but it feels much less well rounded. I have no doubt that Google have both the infrastructure and the expertise to curb stomp everyone else, should they resolve in earnest to do so. Lest we forget, "Attention is All You Need" came from Google.

Interesting, glad to hear. We have gemma4 at work, and I was considering localhosting qwen, but gemma4 is so far behind the Opus and Fable I have at home that I've decided to hold off for another model release.

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#436

Post by Eridrus »

sdesol wrote: post #223
Eridrus wrote: post #213

Earlier quoted context omitted.

I don't think it's that early tbh, agentic coding has ~90% adoption in the US. Claude Code has largely won individual developer mindshare and has been on top ever since it came out. The benchmarks change, but almost nobody opts to use anything other than Claude IME when I ask them. Enterprise is more competitive since they care about costs and other things, but developers leaning towards Claude puts a thumb on the sc…

> Claude Code has largely won individual developer mindshare and has been on top ever since it came out. Claude Code's success is not due to the agent but because the model is considered the best for programming and is very heavily subsidized, compared to pay as you go API prices. Consumers and Enterprise are not really locked in and will go where it makes the most sense. I think they have almost no loyalty by actual…

This isn't a perfect survey, but I am a Codex user and most of my employees are pretty stuck in their workflows and were not really interested in trying even when I was saying good things (even pre-Opus 4.8).

When we work trial people, 100% of people ask for Claude rather than Codex or anything else.

When I talk to people at non-AI tech events everyone basically says they use Claude and have not tried an alternative.

Developers writ large are actually not that interested in trying multiple tools, they like customizing their chosen tool and tweaking it forever.

I think developers are as susceptible to brand marketing as everyone else. It's why almost everyone has a Macbook.

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#437

Post by WarmWash »

onlyrealcuzzo wrote: post #415
awongh wrote: post #193

Earlier quoted context omitted.

It seems like there are some credible rumors that Google is actually winning in terms of actually building models that work and don't lose money- between how they're able to price them, the TPU advantage and their capex advantage (being able to raise debt + just having a lot of cash - well I said not lose money... more like not go bankrupt). From the outside they look like they're behind in terms of frontier models,…

It's rumored that Gemini 3.5 flash has a >50% margin, and I'd imagine 3.6 flash is even higher. I do not think OpenAI or Anthropic are actively chasing margins - though, Anthropic is supposed to be profitable on some form of non-GAAP accounting... I suspect Google isn't really interested in seeing how far it can get dragged into a race of selling dollars for $0.25, and is more interested to see if it can stay in the…

It kind of doesn't make sense though, because typically a large org like Google can afford to crush competitors on pricing. They could probably even go toe to toe with chinese model pricing for years without feeling it.

Maybe they don't want to price war with the other labs so they can comfortably maintain healthy margins on selling them compute?

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#438

Post by zwaps »

postalcoder wrote: post #53

I wonder how big the Pro model is that Google is using behind the scenes to train these smaller ones. Going on baseless speculation, the lack of accompanying pro models with these flash releases either means: 1) the model is too big to be economical, 2) google doesn't have the compute to serve the big model, 3) their big model has too many alignment issues to serve to the public. edit: looks like benchmarks are up on…

More likely they don't manage to advance benchmarks on the SOTA level anymore. In other words: They can't beat 5.6 nor Fable

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#439

Post by Eridrus »

draebek wrote: post #331
Eridrus wrote: post #213

Earlier quoted context omitted.

I don't think it's that early tbh, agentic coding has ~90% adoption in the US. Claude Code has largely won individual developer mindshare and has been on top ever since it came out. The benchmarks change, but almost nobody opts to use anything other than Claude IME when I ask them. Enterprise is more competitive since they care about costs and other things, but developers leaning towards Claude puts a thumb on the sc…

> I don't think it's that early tbh, agentic coding has ~90% adoption in the US. Where does that 90% figure come from?

I pulled it out of my ass based on anecdotes of talking to engineers and customers, but actual surveys back this up as well with numbers from 84-91%: https://www.digitalapplied.com/blog/ai-coding-adoption-stati...

Re: Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

#440

Post by lynguist »

dTal wrote: post #358
awongh wrote: post #193

Earlier quoted context omitted.

It seems like there are some credible rumors that Google is actually winning in terms of actually building models that work and don't lose money- between how they're able to price them, the TPU advantage and their capex advantage (being able to raise debt + just having a lot of cash - well I said not lose money... more like not go bankrupt). From the outside they look like they're behind in terms of frontier models,…

In terms of open models, Gemma 4 beats the pants off everything else to the point that paying for APIs becomes hard to justify. Qwen has the meme-share for coding, but it feels much less well rounded. I have no doubt that Google have both the infrastructure and the expertise to curb stomp everyone else, should they resolve in earnest to do so. Lest we forget, "Attention is All You Need" came from Google.

> "Attention is All You Need" came from Google

It also came directly from the university of Toronto, and the university of Toronto seeded all American frontier labs (including Grok (why do you think they could start so fast))

Post reply on HN