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

281–290 of 699 posts

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#281

Post by greenavocado »

aero142 wrote: post #234
owlninja wrote: post #203

Earlier quoted context omitted.

Same here. I see so many people obsessing over the latest most state of the art bleeding edge models and yelling at Google for not being there, but I feel like the vast majority of people don't actually need those models. Flash has just been super useful and incredibly fast in my experience.

I prefer luna for most development, especially when I am guiding the process. Sometimes terra. I have had terrible results coding with sol. It is way over-tuned on RL to make something that completes the task, no matter what. I end up with way too much code that does a lot of things I didn't ask for.

IME you're supposed to have Sol drive Luna sub-agents to do 90% of the work. Sol should primarily be the verifier and goal setter. Use omp.sh with Task Delegation -> Always to strongly encourage Sol to drive Lunas. Also Luna prefers to be talked to with English in XML.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#282

Post by BlackRabbit1 »

porridgeraisin wrote: post #169
BlackRabbit1 wrote: post #143

Earlier quoted context omitted.

Can G3.7 use Google Maps for distance grounding?

Yep. It has access to much better route planning tools than the other models. The results are really good IME.

Sounds good!

I've been planing around with LLM-based trip planning for a very long time now as it fits my very ad hoc style of traveling very well.

But distances always had been.. lets say.. difficult.

Will test it with my upcoming trip to Greece then!

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#283

Post by owaiswiz »

raincole wrote: post #218

I don't know if Google is having the worst marketing fumble or the most genius marketing one. Their "flash" models are very comparable to other companies' "pro" or "flagship" models. It seems to be a quite counterintuitive naming convention as it undersells the models. Unless they have an even more powerful Gemini Pro in the oven...?

not saying they do have a beefier pro, but even if they did, isn't the delta between flash vs pro models reduced quite a bit? (e.g glm 5.3 flash vs 5.3, v4 flash vs v4 pro, sonnet 5 vs opus 5)?

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#284

Post by cubefox »

EFLKumo wrote: post #275

Something maybe unfamiliar with you: not about coding but writing. I've asked it to write an argumentative essay, which is a part of "gaokao" (China's university entrance exam), and its work is *extremely* impressive. speaks and writes like a real senior high school student, and the opinions unfold progressively with deep hierarchy. I don't know how the Gemini team reaches this because this kind of Chinese capability…

Nitpick, but in my opinion an LLM is an "it", not a "her" or "he". Using male or female pronouns risks anthropomorphizing them which can lead to unhealthy outcomes.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#285

Post by WASDx »

eis wrote: post #244

3.8 uses nearly twice as many tokens as 3.7. One might be inclined to think that they just increased the thinking budgets... 3.7 used 64M on high: https://artificialanalysis.ai/models/gemini-3-7-flash 3.8 used 120M on high: https://artificialanalysis.ai/models/gemini-3-8-flash Even their own chart showed more than 2x higher cost compared to 3.7: https://storage.googleapis.com/gweb-uniblog-publish-prod/ima...

3.7 high and 3.8 medium are essentially the same on AA intelligence and cost. Output tokens on DeepSWE gives the same picture. So there might be something to it but they have done other things as well. At least the tokens are really fast.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#286

Post by aesthesia »

trentor wrote: post #268
mrdependable wrote: post #239

Earlier quoted context omitted.

Why are the SVGs getting more detailed rather than just more correct than previous models?

Because people tend to like fidelity more than correctness.

It bugs me a little that "fidelity" has connotations other than "faithfulness to an original"---fidelity should be basically the same as correctness here!

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#287

Post by therealmarv »

On my short tests: This model is amazing and the speed makes it feel like another sort of AI.

But it's bad at code reviews (maybe it's the harness agy cli?). Could not get it to same quality level on reviews like Opus, GPT 5.6, Grok. Even tried special code review skills but no luck.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#288

Post by bobtheborg »

Sidio wrote: post #179
andreygrehov wrote: post #170

I don't use Gemini, but I thought `cool, let's give this new model a try`. Opened gemini.google.com, and I'm not even surprised. The drop down gives me the following options: - Flash-Lite - 3.6 Flash [new] - 3.1 Pro The above is why i don't use LLM products from Google. If the model is not available right this minute (heck, hours before the release!), then I'm not gonna bother getting back to it tomorrow, because tom…

I'm a paid Gemini subscriber via Workspace Standard accounts and yet I also only have access to 3.6. So frustrating and confusing. Meanwhile Anthropic and OpenAI simply release a model everywhere (Fable on Pro only as a somewhat mild exception).

[flagged]

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#289

Post by simonw »

simonw wrote: post #200

The speed combined with the fact that this thing is really good at HTML JavaScript is pretty exciting. Here's what I got for 1.8 cents and 13 seconds from the prompt "make me a cool thing in html": https://gisthost.github.io/?6a77bc41a81718c6aaa10d4ab243c59f Transcript here (it was part of a chat): https://gist.github.com/simonw/b6149a49d327164d67d62c3d12992...

Here's quite an impressive follow-up. I have a tool which knows how to render Markdown documents with embedded SVG content - I use it for the pelican test.

Since this transcript has HTML in it, I decided to upgrade that tool to also render HTML.

I set Gemini 3.8 Flash the task, using my own VERY shonky coding agent tool (llm-coding-agent) - and it did a solid job.

So now you can see the "cool thing in html" rendered within the Markdown document using code that Gemini 3.8 Flash also wrote: https://tools.simonwillison.net/markdown-svg-renderer?url=ht...

Transcript where it built that is here: https://gist.github.com/simonw/3e36b98292dfdc1b3baff158faa74...

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#290

Post by superze »

sawjet wrote: post #277
wayeq wrote: post #260

Earlier quoted context omitted.

> That's both cool and fast. and probably a barely modified knock-off of some github project that it trained on

You're so upset that you have to invent an imaginary hypothesis to make yourself feel better.

Yes, very imaginary to think that the code comes from pretrained data and copy pasting whole blocks. It's not like this is exactly how LLMs work.
Post reply on HN