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

Gemini 3 Pro: the frontier of vision AI

blog.google

Post reply on HN
Print view View original

281–290 of 309 posts

Re: Gemini 3 Pro: the frontier of vision AI

#281

Post by runarberg »

Workaccount2 wrote: post #249
runarberg wrote: post #127

Earlier quoted context omitted.

> Categories of _what_, exactly? Precisely. At least apples and oranges are both fruits, and it makes sense to compare e.g. the sugar contents of each. But an LLM model and the human brain are as different as the wind and the sunshine. You cannot measure the windspeed of the sun and you cannot measure the UV index of the wind. Your choice of the words here was rather poor in my opinion. Statistical models do not have…

It's easy to handwave away if you assign arbitrary analogies though. If we stay on topic, it's much harder to do since we don't actually know how the brain works. Outside at least that it is a computer doing (almost certainly) analog computation. Years ago I built a quasi mechanical calculator. The computation was done mechanically, and the interface was done electronically. From a calculators POV it was an abominati…

But we do know how the brain works, we have extensively studied the brain, it is probably one of the most studied phenomena in our universe (well barring alien science) and we do know it is not a computer but a neural network[1].

I don’t believe the brain is a trans-physical magic soul box, nor do I think an LLM is doing anything similar to an LLM (apart from some superficial similarities; some [like the artificial neural network] are in an LLMs because it was inspire by the brain).

We use the term cognition to describe the intrinsic properties of the brain, and how it transforms stimulus to a response, and there are several fields of science dedicated to study this cognition.

Just to be clear, you can describe the brain as a computer (a biological computer; totally distinct from a digital, or even mechanical computers), but that will only be an analogy, or rather, you are describing the extrinsic properties of the brain which it happens to share some of which with some of our technology.

---

1: Note, not an artificial neural network, but an OG neural network. AI models were largely inspired by biological brains, and in some parts model brains.

Re: Gemini 3 Pro: the frontier of vision AI

#282

Post by skybrian »

willis936 wrote: post #153
knollimar wrote: post #33

I do some electrical drafting work for construction and throw basic tasks at LLMs. I gave it a shitty harness and it almost 1 shotted laying out outlets in a room based on a shitty pdf. I think if I gave it better control it could do a huge portion of my coworkers jobs very soon

I would really love a magic wand to make things like AVEVA and AutoCAD not so painful to use. You know who should be using tools to make these tools less awful? AVEVA and AutoCAD. Engineers shouldn't be having to take on risk by deferring some level of trust to third party accelerators with poor track records.

I think that, much like LLM’s are specifically trained to be good at coding and good at being agents, we’re going to need better benchmarks for CAD and spatial reasoning so the AI labs can grind on them.

A good start would be getting image generators to understand instructions like “move the table three feet to the left.”

Re: Gemini 3 Pro: the frontier of vision AI

#283

Post by cubefox »

Workaccount2 wrote: post #48

Well It is the first model to get partial-credit on an LLM image test I have. Which is counting the legs of a dog. Specifically, a dog with 5 legs. This is a wild test, because LLMs get really pushy and insistent that the dog only has 4 legs. In fact GPT5 wrote an edge detection script to see where "golden dog feet" met "bright green grass" to prove to me that there were only 4 legs. The script found 5, and GPT-5 the…

Gemini 3 Pro correctly counted the fingers in this picture:

https://imagazine.pl/wp-content/uploads/2024/12/ugly-AI-pic-...

GPT-5 couldn't do it.

Re: Gemini 3 Pro: the frontier of vision AI

#284

Post by skybrian »

Workaccount2 wrote: post #251
Fraterkes wrote: post #115

Earlier quoted context omitted.

The turing test is still a thing. No llm could pass for a person for more than a couple minutes of chatting. That’s a world of difference compared to a decade ago, but I would emphatically not call that “passing the turing test” Also, none of the other things you mentioned have actually happened. Don’t really know why I bother responding to this stuff

Ironically the main tell of LLMs is that are too smart and write too well. No human can discuss the depth of topics they can and no humans writes like a author/journalist all the time. i.e. the tell that it's not human is that it is too perfectly human. However if we could transport people from 2012 to today to run the test on them, none would guess the LLM output was from a computer.

That’s not the Turing Test; it’s just vaguely related. The Turing Test is an interactive party game of persuasion and deception, sort of like playing a werewolves versus villagers game. Almost nobody actually plays the game.

Also, the skill of the human opponents matters. There’s a difference between testing a chess bot against randomly selected college undergrads versus chess grandmasters.

Just like jailbreaks are not hard to find, figuring out exploits to get LLM’s to reveal themselves probably wouldn’t be that hard? But to even play the game at all, someone would need to train LLM’s that don’t immediately admit that they’re bots.

Re: Gemini 3 Pro: the frontier of vision AI

#285

Post by radarsat1 »

jiggawatts wrote: post #68
danielvaughn wrote: post #57

Earlier quoted context omitted.

I don’t know much about AI, but I have this image test that everything has failed at. You basically just present an image of a maze and ask the LLM to draw a line through the most optimal path. Here’s how Nano Banana fared: https://x.com/danielvaughn/status/1971640520176029704?s=46

The reason is that image generators don't iterate on the output in the same way the text-based LLMs do. Essentially they produce the image in "one hit" and can't solve a complex sequence in the same way you couldn't one-shot this either. Try taking a random maze, glance at it, then go off to draw a squiggle on a transparency. If you were to place that on top of the maze, there's virtually no chance that you'd have fo…

you're kind of describing the figure in table 1 (page 8) of the diffusion forcing paper

https://arxiv.org/abs/2407.01392

of course it doesn't redraw the image on every step, so not exactly what you're suggesting (interesting idea btw) but i think it's relevant.

Re: Gemini 3 Pro: the frontier of vision AI

#286

Post by datadrivenangel »

daemonologist wrote: post #155
simonw wrote: post #45

Earlier quoted context omitted.

I was surprised at how poorly GPT-5 did in comparison to Opus 4.1 and Gemini 2.5 on a pretty simple OCR task a few months ago - I should run that again against the latest models and see how they do. https://simonwillison.net/2025/Aug/29/the-perils-of-vibe-cod...

Agreed, GPT-5 and even 5.1 is noticeably bad at OCR. OCRArena backs this up: https://www.ocrarena.ai/leaderboard (I personally would rank 5.1 as even worse than it is there). According to the calculator on the pricing page (it's inside a toggle at the bottom of the FAQs), GPT-5 is resizing images to have a minor dimension of at most 768: https://openai.com/api/pricing/ That's ~half the resolution I would normally use…

and GPT4 was pretty decent at OCR, so that's weird?

Re: Gemini 3 Pro: the frontier of vision AI

#287

Post by CamperBob2 »

irthomasthomas wrote: post #149
Zambyte wrote: post #125

Earlier quoted context omitted.

I wonder how they would behave given a system prompt that asserts "dogs may have more or less than four legs".

That may work but what actual use would it be? You would be plugging one of a million holes. A general solution is needed.

Not necessarily. The problem may be as simple as the fact that LLMs do not see "dog legs" as objects independent of the dogs they're attached to.

The systems already absorb much more complex hierarchical relationships during training, just not that particular hierarchy. The notion that everything is made up of smaller components is among the most primitive in human philosophy, and is certainly generalizable by LLMs. It just may not be sufficiently motivated by the current pretraining and RL regimens.

Re: Gemini 3 Pro: the frontier of vision AI

#288

Post by knollimar »

akoboldfrying wrote: post #234
8n4vidtmkvmk wrote: post #217

Earlier quoted context omitted.

I still haven't witnessed a serious attempt at passing the Turing test. Are we just assuming its been beaten, or have people tried? Like if you put someone in an online chat and ask them to identify if the person they're talking to is a bot or not, you're telling me your average joe honestly can't tell? A blog post or a random HN comment, sure, it can be hard to tell, but if you allow some back and forth.. i think we…

A couple of months ago I saw a paper (can't remember if published or just on arxiv) in which Turing's original 3-player Imitation Game was played with a human interrogator trying to discern which of a human responder and an LLM was the human. When the LLM was a recent ChatGPT version, the human interrogator guessed it to be the human over 70% of the time ; when the LLM was weaker (I think Llama 2), the human interrog…

The prompt for the LLM was to respond with short phrases, though. I don't know if that's fair since it hides it when there is useful utility.

Re: Gemini 3 Pro: the frontier of vision AI

#289

Post by XenophileJKO »

vunderba wrote: post #201
XenophileJKO wrote: post #137

Earlier quoted context omitted.

It mostly depends on "how" the models work. Multi-modal unified text/image sequence to sequence models can do this pretty well, diffusion doesn't.

Multimodal certainly helps but "pretty well" is a stretch. I'd be curious to know what multimodal model in particular you've tried that could consistently handle generative prompts of the above nature (without human-in-the-loop corrections). For example, to my knowledge ChatGPT is unified and I can guarantee it can't handle something like a 7-legged spider.

I just got the model to generate a spider without a leg by saying "Spider missing one leg" and it did it fine. It won't do it "every time", (in my case 1 out of 2), but it will do it. I used the GPT-image-1 model in the api. I don't think they are actually running a full end to end text/image model sequence model. I don't think anyone really is commercially, they are hybrids as far as I know. Someone here probably has better information on the current architectures.

Re: Gemini 3 Pro: the frontier of vision AI

#290

Post by ithkuil »

Rover222 wrote: post #272
theoa wrote: post #229

Earlier quoted context omitted.

Draw a millipede as a dog: Gemini responds: Conceptualizing the "Millipup" https://gemini.google.com/share/b6b8c11bd32f Draw the five legs of a dog as if the body is a pentagon https://gemini.google.com/share/d74d9f5b4fa4 And animal legs are quite standardized https://en.wikipedia.org/wiki/List_of_animals_by_number_of_l... It's all about the prompt. Example: Can you imagine a dog with five legs? https://gemini.google…

haha fair point, you can get the expected results with the right prompt, but I think it still reveals a general lack of true reasoning ability (or something)

Or it just shows that it tries to overcorrect the prompt which is generally a good idea in the most cases where the prompter is not intentionally asking a weird thing.

This happens all the time with humans. Imagine you're at a call center and get all sorts of weird descriptions of problems with a product: every human is expected to not expect the caller is an expert and actually will try to interpolate what they might mean by the weird wording they use

Post reply on HN