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

191–200 of 285 posts

Re: Improved Gemini 2.5 Flash and Flash-Lite

#191

Post by mastercheif »

Hobadee wrote: post #183

Am I using a different Gemini from everyone else? We have Google Workspace at my job, so Gemini is baked in. It is HORRENDOUS when compared to other models. I hear a bunch of other people talking about how great Gemini is, but I've never seen it. The responses are usually either incorrect, way too long, (essays when I wanted summaries) or just...not...good. I will ask the exact same question to both Gemini and ChatGP…

I agree. I think it comes down OpenAI's superior post-training.

ChatGPT is better at:

A) Interpreting what I'm asking it for me needing to provide additional explicit context.

B) Formatting answers in a way that are easily digestible.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#192

Post by manquer »

JumpCrisscross wrote: post #176
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.

Maybe they’re signalling it’s more of a bug fix?

2.5.1 then .

semantic versioning works for most scenarios.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#194

Post by JumpCrisscross »

manquer wrote: post #192
JumpCrisscross wrote: post #176

Earlier quoted context omitted.

Maybe they’re signalling it’s more of a bug fix?

2.5.1 then . semantic versioning works for most scenarios.

Would that automatically roll over anyone pinging 2.5 via their API?

Re: Improved Gemini 2.5 Flash and Flash-Lite

#195

Post by nico »

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 pretty straightforward to get around

Re: Improved Gemini 2.5 Flash and Flash-Lite

#196

Post by vitorgrs »

herpderperator wrote: post #171
alwillis wrote: post #170

Earlier quoted context omitted.

It's pretty common to refer to models by the month and year they were released. For example, the latest Gemini 2.5 Flash is known as "google/gemini-2.5-flash-preview-09-2025" [1]. [1]: https://openrouter.ai/google/gemini-2.5-flash-preview-09-202...

Or, you know, just Gemini 2.6 Flash. I don't recall the 2.5 version having a date associated with it when it came out, though maybe they are using dates now. In marketing, at least, it's always known as Gemini 2.5 Flash/Pro.

It always had dates... They release multiple versions and update regularly. Not sure if this is the first 2.5 Flash update, but pretty sure Pro had a few updates as well...

This is also the case with OpenAI and their models. Pretty standard I guess.

They don't change the versioning, because I guess they don't consider it to be "a new model trained from scratch".

Re: Improved Gemini 2.5 Flash and Flash-Lite

#198

Post by Fade_Dance »

SilverElfin wrote: post #150
golfer wrote: post #109

Earlier quoted context omitted.

Unfortunately Gemini isn't the only culprit here. I've had major problems with ChatGPT reliability myself.

I think what I am seeing from ChatGPT is highly varying performance. I think this must be something they are doing to manage limitations of compute or costs. With Gemini, I think what I see is slightly different - more like a lower “peak capability” than ChatGPT’s “peak capability”.

I'm fairly sure there's some sort of dynamic load balancing at work. I read an anecdote from someone had a test where they asked it to draw a little image (something like an ascii cat, but probably not exactly that since it seems a bit basic), and if the result came back poor they didn't bother using it until a different time of day.

Of course it could all be placebo, but when you intuitively think about it, somewhere on the road the the hundreds of billions in datacenter capex, one would think that there will be periods where compute and demand are out of sync. It's also perfectly understandable why now would be a time to be seeing that.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#199

Post by rasz »

Threw few short python scripts at 2.5. Got stupid messages like "OMG Significant Flaw!!1 all of your functions have non-obvious dependency on this global variable declared in main, nothing will work if you dont execute main first!!1" I mean sure, technically correct, the best kind of LLM correct.

It kept finding those fatal flaws and starting to explain them to then slowly finish with "oh yes this works as intended".

Re: Improved Gemini 2.5 Flash and Flash-Lite

#200

Post by drgoogle »

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…

> I've been running into it consistently, responses that just stop mid-sentence

I’ve seen that behavior when LLMs of any make or model aren’t given enough time or allowed enough tokens.

Post reply on HN