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

191–200 of 582 posts

Re: Gemini 2.5 Flash

#191

Post by lemming »

simonw wrote: post #156

I spotted something interesting in the Python API library code: https://github.com/googleapis/python-genai/blob/473bf4b6b5a6... class ThinkingConfig(_common.BaseModel): """The thinking features configuration.""" include_thoughts: Optional[bool] = Field( default=None, description="""Indicates whether to include thoughts in the response. If true, thoughts are returned only if the model supports thought and thoughts are…

I maintain an alternative client which I build from the API definitions at https://github.com/googleapis/googleapis, which according to https://github.com/googleapis/python-genai/issues/345 should be the right place. But neither the AI Studio nor the Vertex definitions even have ThinkingConfig yet - very frustrating. In general it's amazing how much API munging is required to get a working client from the public API definitions.

Re: Gemini 2.5 Flash

#192

Post by jeeeb »

zoogeny wrote: post #131

Google making Gemini 2.5 Pro (Experimental) free was a big deal. I haven't tried the more expensive OpenAI models so I can't even compare, only to the free models I have used of theirs in the past. Gemini 2.5 Pro is so much of a step up (IME) that I've become sold on Google's models in general. It not only is smarter than me on most of the subjects I engage with it, it also isn't completely obsequious. The model push…

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.

Re: Gemini 2.5 Flash

#193

Post by chucky_z »

whyenot wrote: post #114
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…

Another advantage that Google has is the deep integration of Gemini into Google Office products and Gmail. I was part of a pilot group and got to use a pre-release version and it's really powerful and not something that will be easy for OpenAI to match.

I have access to this now and I want it to work so bad and it's just proper shit. Absolute rubbish.

They really, truly need to fix this integration. Gemini in Google Docs is barely acceptable, it doesn't work at all (for me) in Gmail, and I've not yet had it do anything other than error in Google Sheets.

Re: Gemini 2.5 Flash

#194

Post by qwertox »

simonw wrote: post #156

I spotted something interesting in the Python API library code: https://github.com/googleapis/python-genai/blob/473bf4b6b5a6... class ThinkingConfig(_common.BaseModel): """The thinking features configuration.""" include_thoughts: Optional[bool] = Field( default=None, description="""Indicates whether to include thoughts in the response. If true, thoughts are returned only if the model supports thought and thoughts are…

In AI Studio the flash moddels has two toggles: Enable thinking and Set thinking budget. If thinking budget is enabled, you can set tue max number of tokens it can use to think, else it's Auto.

Re: Gemini 2.5 Flash

#195

Post by ipsum2 »

minimaxir wrote: post #139

One hidden note from Gemini 2.5 Flash when diving deep into the documentation: for image inputs, not only can the model be instructed to generated 2D bounding boxes of relevant subjects, but it can also create segmentation masks! https://ai.google.dev/gemini-api/docs/image-understanding#se... At this price point with the Flash model, creating segmentation masks is pretty nifty. The segmentation masks are a bit of a g…

The performance is basically so bad it's unusable though, segmentation models and object detection models are still the best, for now.

Re: Gemini 2.5 Flash

#196

Post by ramesh31 »

arnaudsm wrote: post #6

Gemini flash models have the least hype, but in my experience in production have the best bang for the buck and multimodal tooling. Google is silently winning the AI race.

>”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.

Re: Gemini 2.5 Flash

#197

Post by SoftMachine »

transformi wrote: post #7

Bad day is going on google. First the decleration of illegal monopoly.. and now... Google’s latest innovation: programmable overthinking. With Gemini 2.5 Flash, you too can now set a thinking_budget—because nothing says "state-of-the-art AI" like manually capping how long it’s allowed to reason. Truly the dream: debugging a production outage at 2am wondering if your LLM didn’t answer correctly because you cheaped out…

[dead]

Re: Gemini 2.5 Flash

#198

Post by russellbeattie »

arnaudsm wrote: post #6

Gemini flash models have the least hype, but in my experience in production have the best bang for the buck and multimodal tooling. Google is silently winning the AI race.

I have to say, I never doubted it would happen. They've been at the forefront of AI and ML for well over a decade. Their scientists were the authors of the "Attention is all you need" paper, among thousands of others. A Google Scholar search produces endless results. There just seemed to be a disconnect between the research and product areas of the company. I think they've got that worked out now.

They're getting their ass kicked in court though, which might be making them much less aggressive than they would be otherwise, or at least quieter about it.

Re: Gemini 2.5 Flash

#199

Post by stavros »

byearthithatius wrote: post #89
alecco wrote: post #61

Gemini models are very good but in my experience they tend to overdo the problems. When I give it things for context and something to rework, Gemini often reworks the problem. For software it is barely useful because you want small commits for specific fixes not a whole refactor/rewrite. I tried many prompts but it's hard. Even when I give it function signatures of the APIs the code I want to fix uses, Gemini rewrite…

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.

Re: Gemini 2.5 Flash

#200

Post by wavewrangler »

dist-epoch wrote: post #123
jay_kyburz wrote: post #103

Earlier quoted context omitted.

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.

[flagged]

Yeah, general propaganda and psyops are actually more effective around 12% - 15%, we find it is more accurate to the user base, thus is questioned less for standing out more /s
Post reply on HN