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

Gemini 3.5 Flash

blog.google

Post reply on HN
Print view View original

431–440 of 692 posts

Re: Gemini 3.5 Flash

#431

Post by mrbungie »

Alifatisk wrote: post #268

The demo of the model in Antigravity automatically rename and categorize unstructured assets using vision was quite cool, it demodulates that the IDE sidepanel can be used for more than just coding. I wonder if the harness in Antigravity is based on Gemini cli or if they are completely different. Could Gemini cli do the same task? Or is the vision feature a Antigravity thing?

There is now an Antigravity CLI which will replace Gemini CLI. Gemini CLI is going to be EOLd by June 18th afaik. Antigravity CLI and GUI share the same agent harness, so it might do the same task.

Source: https://developers.googleblog.com/an-important-update-transi...

Re: Gemini 3.5 Flash

#432

Post by Culonavirus »

neksn wrote: post #295
reconnecting wrote: post #167

Earlier quoted context omitted.

LLM pre-training models risk being unable to be updated with data from after 2025, as much of it is corrupted with LLM-generated content. We might be locked into outdated knowledge, where only whitelisted sources decide what to include. Taking into account the sometimes blind belief that 'LLMs know everything', the outcome could be very costly, especially for technologies and businesses unfortunate enough to emerge a…

Considering all models can use search engines, is this really relevant?

This is not meant as an insult, but have you actually LLM/vibe coded anything that used a fast(-ish) moving library or framework? Try asking your favorite LLM with say Jan 2025 knowledge cutoff (or pretraining data cutoff, whatever you want to call it) to work on something using a framework that had a big rewrite later that year (which would make it one year old now, which is like ages in the LLM coding era)... It's a nightmare full of wrestling with the LLM when you try to tell it the version of the framework and that it changed a lot from the previous version and yadda yadda long story short down the thread when context runs out and/or is compressed it begins to forget detailed instructions and just falls back to pulling out old patterns it "remembers" from pretraining. And so you need to constantly remind it what you work with and "oh hey this doesnt work because we're working with react router v7 in framework mode, remember? not react router v6". Or try to use the latest non-lts/breaking version of a library, at first it looks it up online, but again as you get deeper into the weeds and little details, the struggle begins.

So, as far as I'm concerned, training cutoff is still a big deal.

Re: Gemini 3.5 Flash

#433

Post by mrbungie »

kristopolous wrote: post #422
esafak wrote: post #372

Earlier quoted context omitted.

I see no 'score' or 'age' mentioned in your script. What does age signify and how are they calculated?

This isn't obvious? "\( 10 \* (.codingIndex // 0) | round / 10 ) \( ( now - ( .releaseDate | try ( strptime("%Y-%m-%d") | mktime ) catch (now + 86400) ) ) / 86400 | floor Real question. I see 86400 and I know it's time... That might just be me. I'm not being an ass, I don't know how to talk to people or when I think I'm being clear but I'm actually being cryptic

It is kind of noisy because the release recency, which is what your "age" column actually represents, is not important data for the comparison you are trying to make.

Also what message we should get from that table is not really obvious.

Re: Gemini 3.5 Flash

#434

Post by dekhn »

simonw wrote: post #131

The pelican is a lot : https://github.com/simonw/llm-gemini/issues/133#issuecomment... Not a great bicycle though, it forgot the bar between the pedals and the back wheel and weirdly tangled the other bars. Expensive too - that pelican cost 13 cents: https://www.llm-prices.com/#it=11&ot=14403&sel=gemini-3.5-fl...

I'm told there is a new Jeff Dean fact inside google: "Jeff Dean manually adjusts the weights in the model just to screw with Simon".

Re: Gemini 3.5 Flash

#435

Post by wslh »

OhMeadhbh wrote: post #177

Am I really so old that when someone says "Flash" my immediate response is... "consider HTML5 instead" ??

Same here, and worst because in another thread users are generating animations.

Re: Gemini 3.5 Flash

#436

Post by Culonavirus »

margorczynski wrote: post #331

Wow at the price hike. Still I think in the long run the Chinese will win if they're able to produce hardware comparable to Nvidia.

Doesn't need to be the Chinese. It can be anyone without stratospheric Nvidia margins. The Gold Rush phase of AI economy (aka "the bubble") is beginning to slow down and the Optimization phase is just beginning to ramp up (we see this with massive bumps to token cost and token burn rate of pretty much all frontier models, plus the general pivot away from your typical individual chat end-users to businesses and employees of said businesses) and there will come a time when "nvidia has the best software stack" will not mean much for the big players. Organically, I think it already kinda does, it's just masked with the inertia of massive circular deals and Nvidia selling its services to itself (entities it backs/invests in).

Re: Gemini 3.5 Flash

#437

Post by sosborn »

irthomasthomas wrote: post #161
simonw wrote: post #131

The pelican is a lot : https://github.com/simonw/llm-gemini/issues/133#issuecomment... Not a great bicycle though, it forgot the bar between the pedals and the back wheel and weirdly tangled the other bars. Expensive too - that pelican cost 13 cents: https://www.llm-prices.com/#it=11&ot=14403&sel=gemini-3.5-fl...

This is a perfect illustration of something I noticed with llm progress. Ask them to improve an svg like this, and it never fixes the missing crossbar or disconnected limbs, it just adds more stuff. In this example they have obviously improved greatly, and it contains a ridiculous amount of detail, but they still to get the basic shape of the frame wrong. It's weird. And the pattern shows up everywhere, try it with a…

This matches my experience with human too FWIW.

Re: Gemini 3.5 Flash

#438

Post by kristopolous »

mrbungie wrote: post #433
kristopolous wrote: post #422

Earlier quoted context omitted.

This isn't obvious? "\( 10 \* (.codingIndex // 0) | round / 10 ) \( ( now - ( .releaseDate | try ( strptime("%Y-%m-%d") | mktime ) catch (now + 86400) ) ) / 86400 | floor Real question. I see 86400 and I know it's time... That might just be me. I'm not being an ass, I don't know how to talk to people or when I think I'm being clear but I'm actually being cryptic

It is kind of noisy because the release recency, which is what your "age" column actually represents, is not important data for the comparison you are trying to make. Also what message we should get from that table is not really obvious.

Okay I think there's a familiarity delta. I constantly run into this

I know artificial analysis quite well as the gold standard in llm evals.

But I guess they're still obscure

I didn't think they were.

The age is important because new techniques keep being developed and so it is a very rough indicator of the size/cost/efficiency trade-off.

How old a model is is a major indicator of what you can expect from it.

I really need to develop a better sense for what people know. That's only one of my problems

Thanks for engaging with me

Re: Gemini 3.5 Flash

#439

Post by whh »

seemaze wrote: post #410
hedgehog wrote: post #136

Earlier quoted context omitted.

That pelican looks like it's in Miami for a crypto conference.

That pelican wears it's sunglasses at night. So it can, so it can keep track of the visions in it's eyes.

Pelican and I need an optometrist urgently
Post reply on HN