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

Improved Gemini 2.5 Flash and Flash-Lite

developers.googleblog.com

Post reply on HN
Print view View original

221–230 of 285 posts

Re: Improved Gemini 2.5 Flash and Flash-Lite

#221

Post by baby »

CuriouslyC wrote: post #90
mips_avatar wrote: post #48

Earlier quoted context omitted.

IMO the race for Latency/TPS/cost is entirely between grok and gemini flash. No model can touch them (especially for image to text related tasks), openai/anthropic seem entirely uninterested in competing for this.

grok-4-fast is a phenomenal agentic model, and gemini flash is great for deep research leaf nodes since it's so cheap, you can segment your context a lot more than you would for pro to ensure it surfaces anything that might be valuable.

why use grok? It seems like it's constantly being throttled in order to appear more right-wing

Re: Improved Gemini 2.5 Flash and Flash-Lite

#223

Post by ayende »

behnamoh wrote: post #209
nico wrote: post #195

Earlier quoted context omitted.

Another issue: Gemini can’t do tool calling and (forced) json output at the same time If you want to use application/json as the specified output in the request, you can’t use tools So if you need both, you either hope it gives you correct json when using tools (which many times it doesn’t). Or you have to do two requests, one for the tool calling, another for formatting At least, even if annoying, this issue is pret…

Does any other provider allow that? what use cases are there for JSON + tool calling at the same time?

OpenAI, Ollama, DeepSeek all do that.

And wanting to programmatically work with the result + allow tool calls is super common.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#224

Post by smittywerben »

davidmckayv wrote: post #53

This really captures something I've been experiencing with Gemini lately. The models are genuinely capable when they work properly, but there's this persistent truncation issue that makes them unreliable in practice. I've been running into it consistently, responses that just stop mid-sentence, not because of token limits or content filters, but what appears to be a bug in how the model signals completion. It's been…

When this happened to me it was because, I can only guess, it was the Gemini servers were overloaded. Symptoms: Gemini model, Opaque API wrapper error, truncated responses. To be fair the Anthropic servers are overloaded a lot too but they have a clear error. I gave Gemini a few days on the bench and it fixed itself without any client side changes. YMMV.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#225

Post by SXX »

brap wrote: post #173
driese wrote: post #141

Earlier quoted context omitted.

Small things like this or the fact that AI studio still has issues with simple scrolling confuse me. How does such a brilliant tool still lack such basic things?

The scrolling in AI Studio is an absolute nightmare and somehow they managed to make it worse. It’s so annoying that you have this super capable model but you interact with it using an app that is complete ass

App was likely built my same LLM...

Re: Improved Gemini 2.5 Flash and Flash-Lite

#226

Post by cerved »

omarspira wrote: post #50
ashwindharne wrote: post #27

Google seems to be the main foundation model provider that's really focusing on the latency/TPS/cost dimensions. Anthropic/OpenAI are really making strides in model intelligence, but underneath some critical threshold of performance, the really long thinking times make workflows feel a lot worse in collaboration-style tools, vs a much snappier but slightly less intelligent model. It's a delicate balance, because thes…

I would be surprised if this dichotomy you're painting holds up to scrutiny. My understanding is Gemini is not far behind on "intelligence", certainly not in a way that leaves obvious doubt over where they will be over the next iteration/model cycles, where I would expect them to at least continue closing the gap. I'd be curious if you have some benchmarks to share that suggest otherwise. Meanwhile, afaik something G…

Yesterday I asked Gemini to recalculate the timestamps of tasks in a sequence of tasks, given it's duration and the previous timestamp. It proceeded to write code which gave results like this

  2025-09-26T14:32:10Z
  2025-09-26T14:32:10Z200s
  2025-09-26T14:32:10Z200s600s
  2025-09-26T14:32:10Z200s600s300s
It then proceeded to talk about how efficient this approach was for thousands of numbers.

Gemini is by far the dumbest LLM I've used

Re: Improved Gemini 2.5 Flash and Flash-Lite

#227

Post by Aeolun »

skerit wrote: post #168
herpderperator wrote: post #164

Serious question: If it's an improved 2.5 model, why don't they call it version 2.6? Seems annoying to have to remember if you're using the old 2.5 or the new 2.5. Kind of like when Apple released the third-gen iPad many years ago and simply called it the "new iPad" without a number.

That's why people called the second version of Sonnet v3.5 simply v3.6, and Anthropic acknowledged that by naming the next version v3.7

Only Anthropic has a slightly understandable version scheme.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#228

Post by Aeolun »

TIPSIO wrote: post #44
zitterbewegung wrote: post #36

Okay this is a nitpick but why wouldn't you increment a part of the version number to signify that there is an improvement? These releases are confusing.

This is also my beef... Anthropic kind of did the same thing [1] except it back-fired recently with the cries of "nerfing". We buy these tokens, which are very hard to do in limited tiers, they expire after only a year, and we don't even know how often the responses are changing in the background. Even a 1% improvement or reduction I would want disclosed. Really scary foundation AI companies are building on IMO. Tran…

Are your tokens at any risk of lasting longer than a year? When I buy them it’s generally because I expect to use them reasonably soonish.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#229

Post by mattnewton »

nico wrote: post #195
davidmckayv wrote: post #53

This really captures something I've been experiencing with Gemini lately. The models are genuinely capable when they work properly, but there's this persistent truncation issue that makes them unreliable in practice. I've been running into it consistently, responses that just stop mid-sentence, not because of token limits or content filters, but what appears to be a bug in how the model signals completion. It's been…

Another issue: Gemini can’t do tool calling and (forced) json output at the same time If you want to use application/json as the specified output in the request, you can’t use tools So if you need both, you either hope it gives you correct json when using tools (which many times it doesn’t). Or you have to do two requests, one for the tool calling, another for formatting At least, even if annoying, this issue is pret…

Back before structured outputs were common among model providers, I used to have a “end result” tool the model could call to get the structured response I was looking for. It worked very reliably.

It’s a bit of a hack but maybe that reliably works here?

Re: Improved Gemini 2.5 Flash and Flash-Lite

#230

Post by perfmode »

omarspira wrote: post #50
ashwindharne wrote: post #27

Google seems to be the main foundation model provider that's really focusing on the latency/TPS/cost dimensions. Anthropic/OpenAI are really making strides in model intelligence, but underneath some critical threshold of performance, the really long thinking times make workflows feel a lot worse in collaboration-style tools, vs a much snappier but slightly less intelligent model. It's a delicate balance, because thes…

I would be surprised if this dichotomy you're painting holds up to scrutiny. My understanding is Gemini is not far behind on "intelligence", certainly not in a way that leaves obvious doubt over where they will be over the next iteration/model cycles, where I would expect them to at least continue closing the gap. I'd be curious if you have some benchmarks to share that suggest otherwise. Meanwhile, afaik something G…

How’d I never hear of Jules? Cool.
Post reply on HN