Live data from Hacker News

Gemini 2.5 Flash

developers.googleblog.com

371–380 of 582 posts

Re: Gemini 2.5 Flash

#371
post #181

Earlier quoted context omitted.

Even as a human programmer I don't actually understand your description of the problem well enough to be confident I could correctly guess your intent. What do you mean by "highlight as you scroll"? I guess you want a single heading highlighted at a time, and it should be somehow depending on the viewport. But even that is ambiguous. Do you want the topmost heading in the viewport? The bottom most? Depending on scrol…

> Even as a human programmer I don't actually understand your description of the problem well enough to be confident I could correctly guess your intent. Yeah, you understand what I meant. The code Gemini gave you implements the behavior, and the AI I used gave me pretty much the same thing. There's a problem with the algorithm tho -- if there's a heading too close to the bottom of the page it will never highlight. T…

I clearly didn't understand what you meant, because you did in fact have additional unstated requirements that I could not even have imagined existed and were not in any way hinted at by your initial spec.

And I still don't know what you want! Like, you want some kind of special case where the last heading is handled differently. But what kind of special case? You didn't specify. "It's wrong, fix it".

Fix it how? When the page is scrolled all the way to the bottom, should the last heading always be highlighted? That would just move the complaint to the second heading from the bottom if three headings fit on the last screen. Add padding? Can't be that, since it's exactly what this solution already did and you thought it wasn't good enough.

Sorry, I will not be playing another round of this. I don't know if you don't realize how inadequate your specifications are (in which case that's your problem with the LLMs too), or if this is some kind of a bit, but either way it doesn't feel like a good use of my time.

But if your problem is that the LLMs give a bad initial answer, get anchored on it, and can't iterate, just give all the requirements up front. If they're requirements you didn't realize existed until you saw the proposed answer, just start again with a fresh context. That tends to work well for me in Aider.

Re: Gemini 2.5 Flash

#372

Dang - Google finally made a quality model that doesn’t make me want to throw my computer out a window. It’s honest, neutral and clearly not trained by the ideologically rabid anti-bias but actually super biased regime. Did I miss a revolt or something in googley land? A Google model saying “free speech is valuable and diverse opinions are good” is frankly bizarre to see.

Downvote me all you want - the fact remains that previous Google models were so riddled with guardrails and political correctness that it was practically impossible to use for anything besides code and clean business data. Random text and opinion would trigger a filter and shut down output.

Even this model criticizes the failures of the previous models.

Re: Gemini 2.5 Flash

#374
post #192

Earlier quoted context omitted.

After comparing Gemini Pro and Claude Sonnet 3.7 coding answers side by side a few times, I decided to cancel my Anthropic subscription and just stick to Gemini.

Just curious, what tool do you use to interface with these LLMs? Cursor? or Aider? or...

I’m on GitHub Copilot with VsCode Insiders, mostly because I don’t have to subscribe to one more thing.

They pretty quick to let you use the latest models nowadays.

Re: Gemini 2.5 Flash

#376

Earlier quoted context omitted.

In my experience they are as dumb as a bag of bricks. The other day I asked "can you edit a picture if I upload one" And it replied "sure, here is a picture of a photo editing prompt:" https://g.co/gemini/share/5e298e7d7613 It's like "baby's first AI". The only good thing about it is that it's free.

Prompt engineering is a thing. Learning how to "speak llm" will give you great results. There's loads of online resources that will teach you. Think of it like learning a new API.

This was using Gemini on my phone - which both Samsung and Google advertise as "just talk to it".

Re: Gemini 2.5 Flash

#377

Genuine naive question: when it comes to Google HN has generally a negative view of it (pick any random story on Chrome, ads, search, web, working at faang, etc. and this should be obvious from the comments), yet when it comes to AI there is a somewhat notable “cheering effect” for Google to win the AI race that goes beyond a conventional appreciation of a healthy competitive landscape, which may appear as a bit of a…

Most of us weren’t using Gemini pro models (1.0, 1.5, 2.0) but the recent 2.5 pro is such a huge step up. It’s better than 3.7 sonnet for coding. Better than o1, o3-mini models and now o3 and o4-mini. It’s become my daily driver. It does everything I need with almost 100% accuracy, is cheap, fast, 1 million context window, uses google web search for grounding, can fetch YouTube video transcripts, can fetch website content, works in google workspace: Gmail, Docs, Sheets. Really hard to beat this combo. Oh and if you subscribe to their AI plan it comes with 2 TB drive storage.

Re: Gemini 2.5 Flash

#378
Gemini has the annoying habit of delegating tasks to me. Most recently I was trying to find out how to do something in FastRawViewer that I couldn't find a straightforward answer on. After hallucinating a bunch of settings and menus that don't exist, it told me to read the manual and check the user forums. So much for saving me time.

Re: Gemini 2.5 Flash

#379
post #62
post #2

50% price increase from Gemini 2.0 Flash. That sounds like a lot, but Flash is still so cheap when compared to other models of this (or lesser) quality. https://developers.googleblog.com/en/start-building-with-gem...

done pretty much inline with the price elo pareto frontier https://x.com/swyx/status/1912959140743586206/photo/1

So if I see it right flash 2.5 doesn't push the pareto front forward, right? It just sits between 2.5 pro and 2.0 flash.

https://storage.googleapis.com/gweb-developer-goog-blog-asse...

Post reply on HN