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

Gemini 2.5 Flash

developers.googleblog.com

Post reply on HN
Print view View original

291–300 of 582 posts

Re: Gemini 2.5 Flash

#291

Post by jofzar »

throwup238 wrote: post #117
mmaunder wrote: post #93

More great innovation from Google. OpenAI have two major problems. The first is Google's vertically integrated chip pipeline and deep supply chain and operational knowledge when it comes to creating AI chips and putting them into production. They have a massive cost advantage at every step. This translates into more free services, cheaper paid services, more capabilities due to more affordable compute, and far more g…

Nobody has really talked about what I think is an advantage just as powerful as the custom chips: Google Books. They already won a landmark fair use lawsuit against book publishers, digitized more books than anyone on earth, and used their Captcha service to crowdsource its OCR. They've got the best* legal cover and all of the best sources of human knowledge already there. Then Youtube for video. The chips of course…

Something that is not specifically called out but is also super relevant is actually the transcription of YouTube videos.

Every video is machine transcribed and stored and then for larger videos the author will often transcribed them themselves.

This is something they have already, it doesn't need any more "work" to get it vs a competitor.

Re: Gemini 2.5 Flash

#292

Post by WiSaGaN »

Interesting that the output price per 1M tokens is $0.6 for non-reasoning, but $3.5 for reasoning. This seems to defy common assumption of how reasoning models work, and you tweak the token probability to control how much thinking it does, but underlying it's the same model and the same inference code path.

Re: Gemini 2.5 Flash

#293

Post by simonw »

blahgeek wrote: post #279
simonw wrote: post #267

An often overlooked feature of the Gemini models is that they can write and execute Python code directly via their API. My llm-gemini plugin supports that: https://github.com/simonw/llm-gemini uv tool install llm llm install llm-gemini llm keys set gemini # paste key here llm -m gemini-2.5-flash-preview-04-17 \ -o code_excution 1 \ 'render a mandelbrot fractal in ascii art' I ran that just now and got this: https://g…

> An often overlooked feature of the Gemini models is that they can write and execute Python code directly via their API. Could you elaborate? I thought function calling is a common feature among models from different providers

The Gemini API runs the Python code for you as part of your single API call, without you having to handle the tool call request yourself.

Re: Gemini 2.5 Flash

#294

Post by vdfs »

akudha wrote: post #4
xnx wrote: 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...

Is this cheaper than DeepSeek? Am I reading this right?

Only if you don't use reasoning

Re: Gemini 2.5 Flash

#295

Post by jofzar »

jdthedisciple wrote: post #212
Nihilartikel wrote: post #202

Earlier quoted context omitted.

100% agree. I had Gemini flash 2 chew through thousands of points of nasty unstructured client data and it did a 'better than human intern' level conversion into clean structured output for about $30 of API usage. I am sold. 2.5 pro experimental is a different league though for coding. I'm leveraging it for massive refactoring now and it is almost magical.

> thousands of points of nasty unstructured client data What I always wonder in these kinds of cases is: What makes you confident the AI actually did a good job since presumably you haven't looked at the thousands of client data yourself? For all you know it made up 50% of the result.

It also depends on what you are using the data for, if it's for non (precise) data based decisions then it's fine. Specially if you looking for "vibe" based decisions before then dedicating time to "actually" process the data for confirmation.

30$ to get an view into data that would take at least x many hours of someone's time is actually super cheap, specially if the decision of that result is then to invest or not invest the x many hours to confirm it.

Re: Gemini 2.5 Flash

#296

Post by jsnell »

nonethewiser wrote: post #264
omneity wrote: post #115

Earlier quoted context omitted.

In my case, I have workloads like this where it’s possible to verify the correctness of the result after inference, so any success rate is better than 0 as it’s possible to identify the “good ones”.

Aren’t you basically just saying you are able to measure the error rate? I mean that’s good, but already a given in this scenario where hes reporting the 7% error rate.

No. If you're able to verify correctness of individual items of work, you can accept the 93% of verified items as-is and send the remaining 7% to some more expensive slow path.

That's very different from just knowing the aggregate error rate.

Re: Gemini 2.5 Flash

#297

Post by jofzar »

tominous wrote: post #236
jdthedisciple wrote: post #212

Earlier quoted context omitted.

> thousands of points of nasty unstructured client data What I always wonder in these kinds of cases is: What makes you confident the AI actually did a good job since presumably you haven't looked at the thousands of client data yourself? For all you know it made up 50% of the result.

In my case I had hundreds of invoices in a not-very-consistent PDF format which I had contemporaneously tracked in spreadsheets. After data extraction (pdftotext + OpenAI API), I cross-checked against the spreadsheets, and for any discrepancies I reviewed the original PDFs and old bank statements. The main issue I had was it was surprisingly hard to get the model to consistently strip commas from dollar values, which…

I hope there is a future where csv comma's don't screw up data. I know it will never happen but it's a nightmare.

Everyone has a story of a csv formatting nightmare

Re: Gemini 2.5 Flash

#298

Post by zoogeny »

teleforce wrote: post #273
zoogeny wrote: post #252

Earlier quoted context omitted.

It's a bit of a fancy way to say "yes man". Like in corporations or politics, if a leader surrounds themselves with "yes men". A synonym would be sycophantic which would be "behaving or done in an obsequious way in order to gain advantage." The connotation is the other party misrepresents their own opinion in order to gain favor or avoid disapproval from someone of a higher status. Like when a subordinate tries to gu…

Yes, that's the first two words that come to my mind when I read the meaning. The Gen Z word now I think is "simp".

Yeah, it is very close. But I feel simp has a bit of a sexual feel to it. Like a guy who does favors for a girl expecting affection in return, or donates a lot of money to an OnlyFans or Twitch streamer. I also see simp used where we used to call it white-knighting (e.g. "to simp for").

Obsequious is a bit more general. You could imagine applying it to a waiter or valet who is annoyingly helpful. I don't think it would feel right to use the word simp in that case.

In my day we would call it sucking up. A bit before my time (would sound old timey to me) people called it boot licking. In the novel "Catcher in the Rye", the protagonist uses the word "phony" in a similar way. This kind of behavior is universally disliked so there is a lot slang for it.

Re: Gemini 2.5 Flash

#299

Post by free_energy_min »

stavros wrote: post #199
byearthithatius wrote: post #89

Earlier quoted context omitted.

Yes, it will add INSANE amounts of "robust error handling" to quick scripts where I can be confident about assumptions. This turns my clean 40 lines of Python where I KNOW the JSONL I am parsing is valid into 200+ lines filled with ten new try except statements. Even when I tell it not to do this, it loves to "find and help" in other ways. Quite annoying. But overall it is pretty dang good. It even spotted a bug I mi…

I didn't realize this was a bigger trend, I asked it to write a simple testing script that POSTed a string to a local HTTP server as JSON, and it wrote a 40 line script, handling any possible error. I just wanted two lines.

same issue here! isn’t even helpful because if the code isn’t working i want it to fail, not just skip over errors

Re: Gemini 2.5 Flash

#300

Post by pplante »

asadotzler wrote: post #277
JFingleton wrote: post #81

Earlier quoted context omitted.

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.

LLM's whole thing is language. They make great translators and perform all kinds of other language tasks well, but somehow they can't interpret my English language prompts unless I go to school to learn how to speak LLM-flavored English? WTF?

I like to think of my interactions with an LLM like I'm explaining a request to a junior engineer or non engineering person. You have to be more verbose to someone who has zero context in order for them to execute a task correctly. The LLM only has the context you provided so they fail hard like a junior engineer would at a complicated task with no experience.
Post reply on HN