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

Gemini 3.8 Flash and 3.8 Flash Cyber

blog.google

Post reply on HN
Print view View original

631–640 of 700 posts

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#631

Post by mark_l_watson »

rahimnathwani wrote: post #133
jampa wrote: post #113

I've been using Gemini 3.7 for my personal trip planning app. Across multiple benchmarks, it ranks higher on everything I tried: - Real world knowledge (when a thing opens and closes, the geographic region, historical facts). It's also the best at taking a cluster of places and working out a visiting order. - Photo ranking (which photo should be the hero). Gemini can tell whether a photo is of the thing or of the vie…

One thing in your comment surprised me: "when a thing opens and closes" Why you would rely on the model's weights to know opening hours, instead of having the model call a web search tool to verify it on the official site?

The Gemini APIs have options for using Google Search grounding, or in simpler terms: to process a prompt by first using search to augment the context.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#632

Post by mark_l_watson »

mft_ wrote: post #582
kridsdale1 wrote: post #337

Earlier quoted context omitted.

Google AI person here: Using grounding in Gemini is indeed backed by the same canonical data source for business information (like opening hours) as Google Maps. This stuff is available in its own API for a GCP fee, but we’ve built tooling to connect it to the Gemini agentic ecosystem as well.

So if I understand you correctly, Gemini has direct free access to the Google Maps API in a manner that others (people, LLMs) would need to sign up for API access and pay for?

That is my understanding, which is a nice thing. I use Exa and Brave search APIs separately but the Google bundling is convenient.

Ollama Cloud offers the same thing: they supply a web search tool bundled with cloud API inference services.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#633

Post by rahimnathwani »

mark_l_watson wrote: post #631
rahimnathwani wrote: post #133

Earlier quoted context omitted.

One thing in your comment surprised me: "when a thing opens and closes" Why you would rely on the model's weights to know opening hours, instead of having the model call a web search tool to verify it on the official site?

The Gemini APIs have options for using Google Search grounding, or in simpler terms: to process a prompt by first using search to augment the context.

Right, I mentioned that here: https://news.ycombinator.com/item?id=49539339

jampa was saying that the Gemini 3.7 (a model) ranks higher on real-world knowledge. The point I was originally making is that I would trust any model by itself to answer real-world knowledge problems. If I want to know opening hours, then probably any of the models could find the answer with a web search tool.

Perhaps the Gemini API makes this easier, as the web search tool is built in.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#634

Post by mark_l_watson »

robotmay wrote: post #227
jampa wrote: post #113

I've been using Gemini 3.7 for my personal trip planning app. Across multiple benchmarks, it ranks higher on everything I tried: - Real world knowledge (when a thing opens and closes, the geographic region, historical facts). It's also the best at taking a cluster of places and working out a visiting order. - Photo ranking (which photo should be the hero). Gemini can tell whether a photo is of the thing or of the vie…

I've swapped over to it in the past two weeks, it's been really good. It does what I ask and doesn't think it knows better than me, which so far has made it the most pleasing experience I've had when slop-coding. My only wish is it were somewhat cheaper, as it tends to balloon pretty quickly when I'm using it in Opencode. I'm currently trying to offload a lot of work to subagents to stop the context expanding so rapi…

I usually use OpenCode for all open weight models but for Gemini I use Google’s agy coding harness (or my own).

Venders coupling coding harnesses with their own models is usually a good thing. Poolside.ai has a combined harness with their own models that works well locally, and the DeepSeek harness with their models is very interesting.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#637

Post by mark_l_watson »

brap wrote: post #309

People have been sleeping on Gemini lately but these last few Flash releases (which were very rapid) are damn good. These sort of fast and cheap models are great for tasks that are verifiable and can be retried infinitely (like coding), you can basically get frontier results with a good harness (at a fraction of the time and money).

I agree.

I might be wrong about this, but obviously Google would like to provide inferencing at the lowest cost to themselves, so perhaps their slow ‘pro’ releases and rapid ‘flash’ releases is an attempt to guide people to use more profitable models?

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#638

Post by FartinMowler »

p_l wrote: post #404
mattlondon wrote: post #11

Wow this comes after what - 3 or 4 weeks since 3.7 Flash, which was also 3 or 4 weeks after 3.6 Flash IIRC? I eagerly wait more info but sounds like Deepmind without Demis calling the shots has been unleashed and are operating at full speed? Shocker! At this point it is a meme of course, but where is 3.5 Pro :)

Now i am awaiting Gemini 3.11 "For Workgroups" to be released early December...

Wow, that activated a long dormant neuron. IIRC 3.11 main purpose was to make the 3.1 in OS/2 incompatible.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#639

Post by mark_l_watson »

nxdmum wrote: post #579
mvdtnz wrote: post #314

Earlier quoted context omitted.

As someone who has stubbornly stuck with Claude Code, what's a good harness for Gemini models?

If you're on their subscription plan - agy cli or antigravity ui is the only choice i think. Anyway - if you're a dev - you would be writing your own agentic env right ? that's the best way forward. I wont tell you more than this . but if you're not - you are losing out .

I agree, I use my own harness (link to the most stable version, from my Racket book: https://github.com/mark-watson/Racket-AI-book/tree/main/sour...) and except for handling user interrupts correctly, writing harnesses that are customized to your workflow is fairly easy.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#640

Post by mark_l_watson »

mredigonda wrote: post #443
dcchambers wrote: post #426

Earlier quoted context omitted.

Can you use Pi with a Google Pro AI sub or do you need to use API billing?

Using API billing would be a bummer because, as far as I know, there's no way to set up a spend cap or pre-pay the API key, correct?

It is trivial to set up a spending cap on Google Cloud and also on Google AI Studio.

That said, it is probably easier to use APIs from FireWorks.ai, Ollama Cloud, Open Router, etc.

Post reply on HN