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

521–530 of 582 posts

Re: Gemini 2.5 Flash

#521

Post by johnisgood »

xbmcuser wrote: post #520
johnisgood wrote: post #469

Earlier quoted context omitted.

Thanks, will give it a try.

Uploading files on google is now great. I uploaded my python script and the text data files I was using the script to process. I asked it how best to optimize the code. It actually ran the python code on the data files. Then recommended changes then when prompted ran the script again to show the new results. At first I was like maybe hallucinating but no the data was correct.

Yeah "they" run Python code now quite well. They generate some output using Python "internally" (albeit shows you the code).

Re: Gemini 2.5 Flash

#522

Post by andrei_says_ »

summerlight wrote: post #239
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.

Though the same logic can be applied to everywhere, right? Even if it's done by human interns, you need to audit everything to be 100% confident or just have some trust on them.

Not the same logic because interns can make meaning out of the data - that’s built-in error correction.

They also remember what they did - if you spot one misunderstanding, there’s a chance they’ll be able to check all similar scenarios.

Comparing the mechanics of an LLM to human intelligence shows deep misunderstanding of one, the other, or both - if done in good faith of course.

Re: Gemini 2.5 Flash

#523

Post by sweca »

aerhardt wrote: post #510

I am only on OpenAI because they have a native Mac app. Call me old-school but my preferred workflow is still for the most part just asking narrow questions and copying-pasting back and forth. I've been playing with Junie (Jetbrain's AI agent) for a couple of days, but I still don't trust agents to run loose in my codebase for any sizeable amount of work. Does anyone know if Google is planning native apps? Or any wra…

Raycast[0] has Gemini support in their AI offering and it's native, fast and intuitive.

[0] https://raycast.com/ai

Re: Gemini 2.5 Flash

#524

Post by summerlight »

deanmoriarty wrote: post #178

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…

Because now it has brought real competitions to the field. GPT was the king and Claude had been the only meaningful challenger for a while but OpenAI didn't care about Anthropic but just be obsessed with Google. Gemini took a quite time to set the pipeline so initial version was not enough to push the frontier; you remember the days when Google released a new model, OpenAI just responded with some old models in their silo within a day only to crush them. That does not happen anymore and they're forced to develop a better model.

Re: Gemini 2.5 Flash

#526

Post by renewiltord »

thegeomaster wrote: post #509
renewiltord wrote: post #502

Earlier quoted context omitted.

All the communities where people think LLMs are junk love Gemini. Makes me sceptical that the enthusiasm is useful signal. I found the full 2.0 useful for transcription of images. Very good OCR. But not a good assistant. Stalls often and once it has, loses context easily.

Is it possible that a community of people who are constantly pushing LLMs to their limits would be most aware of their limitations, and so more inclined to think they are junk? In terms of business utility, Google has had great releases ever since the 2.0 family. Their models have never missed some mark --- either a good price/performance ratio, insane speeds, novel modalities (they still have the only API for autore…

Just the fact that everyone on HN is always telling us how LLMs are useless but that Gemini is the best of them convinces me of the opposite. No one who can't find a use for this technology is really informed on the subject. Hard to take them seriously.

Re: Gemini 2.5 Flash

#527

Post by mdhb »

blueyes wrote: post #229
jeeeb wrote: 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.

One of the main advantages Anthropic currently has over Google is the tooling that comes with Claude Code. It may not generate better code, and it has a lower complexity ceiling, but it can automatically find and search files, and figure out how to fix a syntax error fast.

Firebase Studio is the Google equivalent

Re: Gemini 2.5 Flash

#528

Post by sweca »

Honestly, the best part about Gemini, especially as a consumer product, is their super lax, or lack thereof, ratelimits. They never have capacity issues, unlike Claude which always feels slow or sometimes outright rejects requests during peak hours. Gemini is constantly speedy and has extremely generous context window limits on the Gemini apps.

Re: Gemini 2.5 Flash

#530

Post by sweca »

zenkey wrote: post #317

Google is totally back in the game now, but it’s still going to take a lot more for them at this point to overcome OpenAI’s “first‑mover advantage” (clearly the favorite among younger users atm).

Google Pixel marketing is doing wonders for Gemini in young populations. I have been seeing a lot more of their phones in my generation's hands.
Post reply on HN