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

541–550 of 582 posts

Re: Gemini 2.5 Flash

#541

Post by lyu07282 »

asim wrote: post #504

I just wish the whole industry would stop using terms like thinking and reasoning. This is not what's happening. If we could come up with more appropriate terms that don't treat these models like they're human then we'd be in a much better place. That aside, it's cool to see the advancement of Google's offering.

Do you think any machine will ever be able to think and/or reason? Or is that a uniquely human thing? and do you have a rational standard to judge when something is reasoning or thinking, or just vibes?

I'm asking because I wonder how much of that common attitude is just a sort of species-chauvinism. You are feeling anxious because machines getting smarter, you are feeling anger because "they" are taking your job away, but the machine doesn't do that, its people with an ideology that do that, you should be angry at that instead.

Re: Gemini 2.5 Flash

#542

Post by UltraSane »

rat9988 wrote: post #445
UltraSane wrote: post #266

Earlier quoted context omitted.

I had a very interesting long debate/discussion with Gemini 2.5 Pro about the Synapse-Evolve bank debacle among other things. It really feels like debating a very knowledgeable and smart human.

You didn't have a debate, you just researched a question.

All right Mr. Pednatic. Very complex linear algebra created a very convincing illusion of a debate. You happy now?

But good LLMs will take a position and push back at your arguments.

Re: Gemini 2.5 Flash

#543

Post by kaoD »

wkat4242 wrote: post #218
ramesh31 wrote: post #196

Earlier quoted context omitted.

>”Google is silently winning the AI race.” It’s not surprising. What was surprising honestly was how they were caught off guard by OpenAI. It feels like in 2022 just about all the big players had a GPT-3 level system in the works internally, but SamA and co. knew they had a winning hand at the time, and just showed their cards first.

True and their first mover advantage still works pretty well. Despite "ChatGPT" being a really uncool name in terms of marketing. People remember it because they were the first to wow them.

How is ChatGPT bad in terms of marketing? It's recognizable and rolls off the tongue in many many many languages.

Gemini is what sucks from a marketing perspective. Generic-ass name.

Re: Gemini 2.5 Flash

#544

Post by suchar »

danpalmer wrote: post #416
tempaccount420 wrote: post #335

Earlier quoted context omitted.

This is so much cheaper than re-prompting each tool use. I wish this was extended to things like: you could give the model an API endpoint that it can call to execute JS code, and the only requirement is that your API has to respond within 5 seconds (maybe less actually). I wonder if this is what OpenAI is planning to do in the upcoming API update to support tools in o3.

I imagine there wouldn’t bd much of a cost to the provider on the API call there so much longer times may be possible. It’s not like this would hold up the LLM in any way, execution would get suspended while the call is made and the TPU/GPU will serve another request.

They need to keep KV cache to avoid prompt reprocessing, so they would need to move it to ram/nvme during longer api calls to use gpu for another request

Re: Gemini 2.5 Flash

#545

Post by simonw »

kaoD wrote: post #543
wkat4242 wrote: post #218

Earlier quoted context omitted.

True and their first mover advantage still works pretty well. Despite "ChatGPT" being a really uncool name in terms of marketing. People remember it because they were the first to wow them.

How is ChatGPT bad in terms of marketing? It's recognizable and rolls off the tongue in many many many languages. Gemini is what sucks from a marketing perspective. Generic-ass name.

Generative Pre-trained Transformer is a horrible term to have an acronym for.

Re: Gemini 2.5 Flash

#546

Post by sroussey »

jay_kyburz wrote: post #103
spruce_tips wrote: post #27

Earlier quoted context omitted.

i have a high volume task i wrote an eval for and was pleasantly surprised at 2.0 flash's cost to value ratio especially compared to gpt4.1-mini/nano accuracy | input price | output price Gemini Flash 2.0 Lite: 67% | $0.075 | $0.30 Gemini Flash 2.0: 93% | $0.10 | $0.40 GPT-4.1-mini: 93% | $0.40 | $1.60 GPT-4.1-nano: 43% | $0.10 | $0.40 excited to to try out 2.5 flash

Can I ask a serious question. What task are you writing where its ok to get 7% error rate. I can't get my head around how this can be used.

You could be OCRing a page that includes a summation line, then add up all the numbers and check against the sum.

Re: Gemini 2.5 Flash

#547

Post by tough »

bayarearefugee wrote: post #278
blueyes wrote: post #229

Earlier quoted context omitted.

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.

As another person that cancelled my Claude and switched to Gemini, I agree that Claude Code is very nice, but beyond some initial exploration I never felt comfortable using it for real work because Claude 3.7 is far too eager to overengineer half-baked solutions that extend far beyond what you asked it to do in the first place. Paying real API money for Claude to jump the gun on solutions invalidated the advantage of…

Open Codex (A codex fork) that supports gemini and openrouter providers https://github.com/ymichael/open-codex

google models on cli are great.

Re: Gemini 2.5 Flash

#548

Post by kaoD »

simonw wrote: post #545
kaoD wrote: post #543

Earlier quoted context omitted.

How is ChatGPT bad in terms of marketing? It's recognizable and rolls off the tongue in many many many languages. Gemini is what sucks from a marketing perspective. Generic-ass name.

Generative Pre-trained Transformer is a horrible term to have an acronym for.

Do you think the mass market thinks GPT is an acronym? It's just a name. Currently synonymous with AI.

Ask anyone outside the tech bubble about "Gemini" though. You'll get astrology.

Re: Gemini 2.5 Flash

#549

Post by tough »

jm547ster wrote: post #475
xvinci wrote: post #390

Earlier quoted context omitted.

Maybe I am not understanding something here. But there are third party options availabe that to the very same thing (e.g. https://aider.chat/ ) which allow you to plug in a model (or even a combination thereof e.g. deepseek as architect and claude as code writer) of your choice. Therefore the advantage of the model provider providing such a thing doesn't matter, no?

Aider is not agentic - it is interactive by design. Copilot agent mode and Cline would better comparisons.

OpenAI launched codex 2 days ago, there's open forks already that support other providers too

there's also claude code proxy's to run it on local llm's

you can just do things

Re: Gemini 2.5 Flash

#550

Post by yjftsjthsd-h »

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, it's anything that's harder to write than verify. A simple example is a logic puzzle; it's hard to come up with a solution, but once you have a possible answer it's really easy to check it. In fact, it can be easier to vet multiple answers and tell the machine to try again than solve it once manually.
Post reply on HN