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

241–250 of 285 posts

Re: Improved Gemini 2.5 Flash and Flash-Lite

#241

Post by hahn-kev »

someguyiguess wrote: post #218
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.

Google has historically always made bad UX choices like this. Conway’s law definitely applies here. Too many different silos building every Google project.

Most of their products are server based so there's no version really. Also they kill stuff off before it would ever be v2 anyway. Also also, they're still better than Microsoft, see Xbox and Windows.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#242

Post by victorbjorklund »

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?

Let's say you wanna build an app that gives back structured data after a web search. First a tool call to a search api. Then do some reasoning/summar/etc on the data returned by the tool. And finally return JSON.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#243

Post by victorbjorklund »

driese wrote: post #141
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…

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?

It's crazy how Google can create so many really amazing products technically but they fall short just because of basic UI/UX issues.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#245

Post by mupuff1234 »

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…

> Google Workspace at my job, so Gemini is baked in.

I think the "baked in" Gemini models are different, try using Gemini through the actual Gemini site.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#246

Post by tschillaci »

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…

Half my requests get retried because they fail, I've contributed to a ticket in June, with no fix yet.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#247

Post by Moosdijk »

My experience with Gemini is the sole reason I am convinced that there's an AI hype going on. It consistently hallucinates key information which has led me to spend countless hours tracking down which information the output was based on, only to find that it dreamt up the facts that it gave to me.

The way I have come to perceive AI is that it's mostly good at reassuring/reaffirming people's beliefs and ideas than an actual source of truth.

That would not be an issue if it was actually marketed as such, but seeing the "guided learning" function fail time and again makes me think we should be a lot more critical of what we're being told by tech enthusiasts/companies about AI.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#248

Post by ikgn »

I have a small test suite for the voice AI math tutor we built, about 50 tests, mostly about correctly following the system instructions. The newly released Flash 2.5 is much worse than current stable version. Gemini 2.5 pro will fail 2—3 tests. Flash 2.5 stable, which we use in production, fails about 10, and the new one fails 20. Every test runs 3 times and the model has to be right every time. Will look into it more, I haven‘t yet looked into actual output. This is not about solving math, the system follows given solution paths.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#249

Post by niekiepriekie »

pier25 wrote: post #145

The most annoying thing about Gemini is that it can't stop suggesting youtube videos. Even when you ask it to stop doing that, multiple times in the same conversation, it will just keep doing it.

This! I feel he suddenly started doing this even though I've told him to stop. And he knows, every time he tells me he's so sorry. It feels like Google is already monetizing Gemini for their ad market.

Re: Improved Gemini 2.5 Flash and Flash-Lite

#250

Post by CaptainOfCoit »

Imustaskforhelp wrote: post #35
rsc wrote: post #16

Earlier quoted context omitted.

FWIW, the versions are not semver but they do follow a defined and regular version schema: https://ai.google.dev/gemini-api/docs/models#model-versions .

I am seeing a lot of demand for something like a semver for AI models. Could thereotically there could be something like a semver that can be autogenerated from that defined and regular version scheme that you shared? Like, Honestly my idea of it is that I could use something like openrouter and then just change the semver without having to worry about these soooo many things as the schema that you shared y'know? A w…

I'm not sure if this is a joke or not, but in case it isn't: Semver was mostly created so users of libraries could judge if a new release would break the API interfaces or not, by just looking at the version. So unless the first number changed, you're good to go (in theory, in practice this obviously didn't work as expected).

With that in mind, what exactly would semver (or similar) represent for AI models? Setup the proper way, your pipelines should continue working regardless of the model, just that the accuracy or some other metric might change slightly. But there should never be any "breakages" like what semver is supposed to help flag.

Post reply on HN