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

Gemini 3.5 Flash

blog.google

Post reply on HN
Print view View original

311–320 of 692 posts

Re: Gemini 3.5 Flash

#311

Post by WarmWash »

SwellJoe wrote: post #186
dr_dshiv wrote: post #103

Earlier quoted context omitted.

3.1 flash lite — $0.25/$1.50 — plus insanely fast. 3.1 flash lite isn’t quite as good as 3 flash preview (which is the most incredible cheap model… I really love it) — but 3.1 is half the price and the insane speed opens up different use cases. For comparison, Opus models are $5/$25

Opus 4.7 is smarter than even Gemini 3.1 Pro on nearly every metric, though. You're comparing apples to oranges. Gemini 3.1 Flash is somewhere in the neighborhood between current Haiku and Sonnet, I think? Still a better value than the Anthropic models, I guess, which are quite pricey. Since Gemini 3.5 Flash is raising the price to $1.50/$9.00, it's priced between Haiku and Sonnet. If it outperforms Sonnet, it remain…

>Opus 4.7 is smarter than even Gemini 3.1 Pro on nearly every metric,

Outside of coding, claude models are pretty meh. GPT and Gemini are the workhorses of science/math/finance.

Re: Gemini 3.5 Flash

#312

Post by stared »

China: we don’t need to use US models, we can distill them ourself

Google: we don’t need Chinese to distill our models, we can do it ourself

Re: Gemini 3.5 Flash

#313

Post by SwellJoe »

nicce wrote: post #300
SwellJoe wrote: post #234

Earlier quoted context omitted.

I have and use both Claude Code and Gemini CLI, and still don't consider Gemini worth starting for coding except to review Claude's output in critical commits (on a security boundary, maybe broad refactors, etc.), though I try side-by-side every now and then just to see the state of things. I also use Gemini Pro in a security scanning harness to act as a second set of eyes, but Opus is better at finding security bugs…

I would argue that prose is just a prompt issue. GPT 5.5 outout is easier to control whan Gemini by prompting. Having better defaults does not make it necessarily better.

I would disagree. I think it'd take a lot of prompting to make GPT 5.5 not have the underlying personality of GPT, which I find awful. They have knobs in ChatGPT to choose a "professional" tone, which improves it somewhat, but even that is still the worst prose of any leading model.

My default AGENTS.md/CLAUDE.md/etc. is a few sentences from Strunk and White, to try to make all the models not suck at writing. It helps keep the models brief, but it doesn't actually make models with shitty prose have good prose. The relevant portion of my agents file is: "Omit needless words. Vigorous writing is concise. A sentence should contain no unnecessary words, a paragraph no unnecessary sentences, for the same reason that a drawing should have no unnecessary lines and a machine no unnecessary parts." Which might add up roughly the same as "be brief" in the weights, I don't know.

If you have a prompt that makes GPT a decent-to-good writer, I would like to see it.

Gemini produces decent-to-good prose without prompting, which improves if instructed to be concise. The other models, even the frontier models, do not have decent-to-good prose without prompting, and even with prompting, rarely elevate to what I would consider Good Enough. Part of this may be that GPT and Claude models get used a lot more heavily, and so I'm highly tuned into their idiosyncrasies. The heavy use of emojis, the click-bait headline style, etc. that they both use unprompted. All of that is repugnant to me, so anything that doesn't do all that by default, or at least not as aggressively, has a huge leg up.

Re: Gemini 3.5 Flash

#314

Post by CobrastanJorji »

nightski wrote: post #189
OhMeadhbh wrote: post #177

Am I really so old that when someone says "Flash" my immediate response is... "consider HTML5 instead" ??

Very little of what made the Flash culture so fun made its way into HTML5.

I dunno, the tools are kind of there. Browsers have canvases and JavaScript and SVGs and sound. The communities are around; they're just kind of dispersed. There's no one website that is THE place for fun stuff. Instead, there are dozens, and most of them suck.

There's still fun stuff, though. I stumbled upon this bit of insanity just yesterday: https://tykenn.itch.io/trees-hate-you. It would have fit in fabulously with the old Flash sites.

Re: Gemini 3.5 Flash

#315

Post by Fairburn »

Google shot it's shot with that alternative history artwork generation fiasco. Don't know why anyone would be too hot for them now. Dime a dozen at this point.

Re: Gemini 3.5 Flash

#316

Post by qgin »

Fairburn wrote: post #315

Google shot it's shot with that alternative history artwork generation fiasco. Don't know why anyone would be too hot for them now. Dime a dozen at this point.

I think the number of people still holding a grudge for that today is small.

Re: Gemini 3.5 Flash

#317

Post by ZeWaka »

SXX wrote: post #207
wslh wrote: post #55

Earlier quoted context omitted.

Can you try with a more complex story such as "three little pigs"? I tried but it created a storybook instead of the SVG animation. I am looking to partially imitate Godogen [1][2] which is really great, even for animations. [1] https://github.com/htdt/godogen [2] https://drive.google.com/file/d/1ozZmWcSwieZQG0muYjbj7Xjhhlz...

I think it's unreasonable to expect models generate complex stories in single prompt since they trained to be concise, but I tried. This is prompt on top of story with no control buttons request: Now think, plan how to tell this story in a cartoon, make scene outline and then generate SVG animation story for "Three Little Pigs" in self contained HTML page. Just single animation no control buttons. Full prompt in gist…

Wow, Gemini 3.5 Flash surprised me there.

Re: Gemini 3.5 Flash

#318

Post by npn »

flakiness wrote: post #310
npn wrote: post #183

Earlier quoted context omitted.

Unlike other providers, Deepseek does promise that they will lower the price when their Huawei cards arrive in a few more months.

Give me a link. Cannot wait. One PSA is that they have 75% discount right now so it is already cheaper than the full price.

Weird, last time I checked it was right on the pricing page.

But even when it happens I doubt it would be as cheap as it is right now. Enjoy it while it lasts!

Re: Gemini 3.5 Flash

#319

Post by recursive »

holtkam2 wrote: post #174
simonw wrote: post #131

The pelican is a lot : https://github.com/simonw/llm-gemini/issues/133#issuecomment... Not a great bicycle though, it forgot the bar between the pedals and the back wheel and weirdly tangled the other bars. Expensive too - that pelican cost 13 cents: https://www.llm-prices.com/#it=11&ot=14403&sel=gemini-3.5-fl...

at a certain point you're gonna need to change your benchmark because this will end up in the model's training set

I'm sure that certain point came and went many releases ago.

Re: Gemini 3.5 Flash

#320

Post by pqdbr »

In my tests, in real production use cases, it's a hard pass.

It's actually 10-15% slower and also more expensive than Gemini 3.1 Pro, because it thinks more than 2.5x Gemini 3.1 Pro.

So that thinking verbosity nullifies the speed and cost gains.

AND the quality is worse than 3.1 Pro for our use cases, making mistakes Pro doesn't make.

Post reply on HN