Gemini 3 Pro: the frontier of vision AI • Hacker News Board

Re: Gemini 3 Pro: the frontier of vision AI

#291

Post by adastra22 » Sat, Dec 06, 2025, 9:41 PM UTC

runarberg wrote: post #278

adastra22 wrote: post #239

Earlier quoted context omitted.

Training is kinda like curve fitting, but inference is not. The inference algorithm is random sampling from a next-token probability distribution. It’s a subtle distinction, but I think an important one in this case, because if it was interpolation then genuine creativity would not be possible. But the attention mechanism results in model building in latent space, which then affects the next token distribution.

I’ve seen both opinions on this in the philosophy of statistics. Some would say that machine learning inference is something other then curve fitting, but others (and I subscribe to this) believe it is all curve fitting. I actually don‘t think which camp is right is that important but I do like it when philosophers ponder about these tings. My reasons to subscribing to the latter camp is that when you have a distribu…

I get the argument that pulling from a distribution is a form of curve fitting. But unless I am misunderstanding, the claim is that it is a curve fitting / interpolation between the training data. The probability distribution generated in inference is not based on the training data though. It is a transform of the context through the trained weights, which is not the same thing. It is the application of a function to context. That function is (initially) constrained to reproduce the training data when presented with a portion of that data as context. But that does not mean that all outputs are mere interpolations between training datapoints.

Except in the most technical sense that any function constrained to meet certain input output values is an interpolation. But that is not the smooth interpolation that seems to be implied here.

Re: Gemini 3 Pro: the frontier of vision AI

#292

Post by Kiro » Sat, Dec 06, 2025, 10:48 PM UTC

runarberg wrote: post #158

Benjammer wrote: post #150

Earlier quoted context omitted.

Wind and sunshine are both types of weather, what are you talking about?

They both affect the weather, but in a totally different way, and by completely different means. Similarly the mechanisms in which the human brain produces output is completely different from the mechanism in which an LLM produces output. What I am trying to say is that the intrinsic properties of the brain and an LLM are completely different, even though the extrinsic properties might appear the same. This is also t…

Artificial cognition has been an established term long before LLMs. You're conflating human cognition with cognition at large. Weather and cognition are both categories that contain many different things.

Re: Gemini 3 Pro: the frontier of vision AI

#293

Post by visioninmyblood » Sat, Dec 06, 2025, 11:01 PM UTC

Rover222 wrote: post #64

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…

I just tried to get Gemini to produce an image of a dog with 5 legs to test this out, and it really struggled with that. It either made a normal dog, or turned the tail into a weird appendage. Then I asked both Gemini and Grok to count the legs, both kept saying 4. Gemini just refused to consider it was actually wrong. Grok seemed to have an existential crisis when I told it it was wrong, becoming convinced that I ha…

I tried this by using an gemini visual agent build with orion from vlm.run. it was able to produce two different images with five leg dog. you need to make it play with itself to improve and correct.

https://chat.vlm.run/c/62394973-a869-4a54-a7f5-5f3bb717df5f

Here is the though process summary(you can see the full thinking the link above):

"I have attempted to generate a dog with 5 legs multiple times, verifying each result. Current image generation models have a strong bias towards standard anatomy (4 legs for dogs), making it difficult to consistently produce a specific number of extra limbs despite explicit prompts."

Re: Gemini 3 Pro: the frontier of vision AI

#294

Post by nearbuy » Sat, Dec 06, 2025, 11:41 PM UTC

JamesSwift wrote: post #219

nearbuy wrote: post #216

Earlier quoted context omitted.

It depends whether you're asking it to solve a maze because you just need something that can solve mazes, or if you're trying to learn something about the model's abilities in different domains. If it can't solve a maze by inspection instead of writing a program to solve it, that tells you something about its visual reasoning abilities, and that can help you predict how they'll perform on other visual reasoning tasks…

Again, think about how the models work. They generate text sequentially. Think about how you solve the maze in your mind. Do you draw a line direct to the finish? No, it would be impossible to know what the path was until you had done it. But at that point you have now backtracked several times. So, what could a model _possibly_ be able to do for this puzzle which is "fair game" as a valid solution, other than magica…

First, the thrust of your argument is that you already knew that it would be impossible for a model like Gemini 3 Pro to solve a maze without code, so there's nothing interesting to learn from trying it. But the rest of us did not know this.

> Again, think about how the models work. They generate text sequentially.

You have some misconception on how these models work. Yes, the transformer LLMs generate output tokens sequentially, but it's weird you mention this because it has no relevance to anything. They see and process tokens in parallel, and then process across layers. You can prove, mathematically, that it is possible for a transformer-based LLM to perform any maze-solving algorithm natively (given sufficient model size and the right weights). It's absolutely possible for a transformer model to solve mazes without writing code. It could have a solution before it even outputs a single token.

Beyond that, Gemini 3 Pro is a reasoning model. It writes out pages of hidden tokens before outputting any text that you see. The response you actually see could have been the final results after it backtracked 17 times in its reasoning scratchpad.

Re: Gemini 3 Pro: the frontier of vision AI

#295

Post by runarberg » Sun, Dec 07, 2025, 12:13 AM UTC

Kiro wrote: post #292

runarberg wrote: post #158

Earlier quoted context omitted.

They both affect the weather, but in a totally different way, and by completely different means. Similarly the mechanisms in which the human brain produces output is completely different from the mechanism in which an LLM produces output. What I am trying to say is that the intrinsic properties of the brain and an LLM are completely different, even though the extrinsic properties might appear the same. This is also t…

Artificial cognition has been an established term long before LLMs. You're conflating human cognition with cognition at large. Weather and cognition are both categories that contain many different things.

Yeah, I looked it up yesterday and saw that artificial cognition is a thing, though I must say I am not a fan and I certainly hope this term does not catch. We are already knee deep in bad terminology because of artificial intelligence (“intelligence” already being extremely problematic even with out the “artificial” qualifier in psychology) and machine learning (the latter being infinitely better but still not without issues).

If you can‘t tell I find issues when terms are taken from psychology and applied to statistics. The terminology should flow in the other direction, from statistics and into psychology.

So my background is that I have done both undergraduate in both psychology and in statistics (though I dropped out of statistics after 2 years) and this is the first time I hear about artificial cognition, so I don‘t think this term is popular, and a short internet search seems to confirm that suspicion.

Out of context I would guess artificial cognition would mean something similar to cognition as artificial neural networks do to neural networks, that is, these are models that simulate the mechanisms of human cognition and recreate some stimulus → response loop. However my internet search revealed (thankfully) that this is not how researches are using this (IMO misguided) term.

https://psycnet.apa.org/record/2020-84784-001

https://arxiv.org/abs/1706.08606

What the researchers mean by the term (at least the ones I found in my short internet search) is not actual machine cognition, nor claims that machines have cognition, but rather an approach of research which takes experimental designs from cognitive psychology and applies them to learning models.

Re: Gemini 3 Pro: the frontier of vision AI

#296

Post by nl » Sun, Dec 07, 2025, 4:34 AM UTC

JamesSwift wrote: post #261

nl wrote: post #253

Earlier quoted context omitted.

> So, what could a model _possibly_ be able to do for this puzzle which is "fair game" as a valid solution, other than magically know an answer by pulling it out of thin air? Represent the maze as a sequence of movements which either continue or end up being forced to backtrack. Basically it would represent the maze as a graph and do a depth-first search, keeping track of what nodes it as visited in its reasoning tok…

And my question to you is “why is that substantially different than writing the correct algorithm to do it”? Im arguing its a myopic view of what we are going to call “intelligence”. And it ignores how human thought works in the same way by using abstractions to move to the next level of reasoning. In my opinion, being able to write the code to do the thing is effectively the same exact thing as doing the thing in te…

> In my opinion, being able to write the code to do the thing is effectively the same exact thing as doing the thing

That's great, but it's demonstrably false.

I can write code that calculates the average letter frequency across any Wikipedia article. I can't do that in my head without tools because of the rule of seven[1].

Tool use is absolutely an intelligence amplifier but it isn't the same thing.

> Because again, the actual “model” is just a text autocomplete engine and it generates from left to right.

This is technically true, but somewhat misleading. Humans speak "left to right" too. Specifically, LLMs do have some spatial reasoning ability (which is what you'd expect with RL training: otherwise they'd just predict the most popular token): https://snorkel.ai/blog/introducing-snorkelspatial/

[1] https://en.wikipedia.org/wiki/The_Magical_Number_Seven,_Plus...

Re: Gemini 3 Pro: the frontier of vision AI

#297

Post by menaerus » Sun, Dec 07, 2025, 8:49 AM UTC

michaelmrose wrote: post #263

menaerus wrote: post #235

Earlier quoted context omitted.

You know, I had a potential hire last week, and I was interviewing this one guy whose resume was really strong, it was exceptional in many ways plus his open-source code was looking really tight. But at the beginning of the interview, I always show the candidates the same silly code example with signed integer overflow undefined behavior baked in. I did the same here and asked him if he sees anything unusual with it,…

Does the ability to verbally detect gotchas in short conversations dealing only with text on a screen or white board really map to stronger candidates? In actual situations you have documentation, editor, tooling, tests, and are a tad less distracted than when dealing with a job interview and all the attendant stress. Isn't the fact that he actually produces quality code in real life a stronger signal of quality?

It's bias and, from my experience, many people do not know how to assess the interviewee to extract his best. My example was luckily just a plastic example that sarcastically portrays how people nowadays are assessing LLM capabilities too. No difference.

Re: Gemini 3 Pro: the frontier of vision AI

#298

Post by dostick » Sun, Dec 07, 2025, 9:31 AM UTC

Rover222 wrote: post #64

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…

I just tried to get Gemini to produce an image of a dog with 5 legs to test this out, and it really struggled with that. It either made a normal dog, or turned the tail into a weird appendage. Then I asked both Gemini and Grok to count the legs, both kept saying 4. Gemini just refused to consider it was actually wrong. Grok seemed to have an existential crisis when I told it it was wrong, becoming convinced that I ha…

Of course if you put the leg there it’s confusing. Just give it AGIP logo as a test.

Re: Gemini 3 Pro: the frontier of vision AI

#299

Post by rglullis » Sun, Dec 07, 2025, 10:05 AM UTC

JamesSwift wrote: post #264

rglullis wrote: post #225

Earlier quoted context omitted.

By your analogy, the developers of stockfish are better chess players than any grandmaster. Tool use can be a sign of intelligence, but "being able to use a tool to solve a problem" is not the same as "being intelligent enough to solve a specific class of problems".

Im not talking about this being the "best maze solver" and "better at solving mazes than humans". Im saying the model is "intelligent enough" to solve a maze. And what Im really saying is that we need to stop moving the goal post on what "intelligence" is for these models, and start moving the goal post on what "intelligence" actually _is_. The models are giving us an existential crisis on not only what it might mean…

> Im saying the model is "intelligent enough" to solve a maze.

And I don't agree. I think that at best the model is "intelligent enough to use a tool that can solve mazes" (which is an entirely different thing) and at worst it is no different than a circus horse that "can do math". Being able to repeat more tricks and being able to select which trick to execute based on the expected reward is not a measure of intelligence.

Re: Gemini 3 Pro: the frontier of vision AI

#300

Post by JamesSwift » Sun, Dec 07, 2025, 11:18 PM UTC

nl wrote: post #296

JamesSwift wrote: post #261

Earlier quoted context omitted.

And my question to you is “why is that substantially different than writing the correct algorithm to do it”? Im arguing its a myopic view of what we are going to call “intelligence”. And it ignores how human thought works in the same way by using abstractions to move to the next level of reasoning. In my opinion, being able to write the code to do the thing is effectively the same exact thing as doing the thing in te…

> In my opinion, being able to write the code to do the thing is effectively the same exact thing as doing the thing That's great, but it's demonstrably false. I can write code that calculates the average letter frequency across any Wikipedia article. I can't do that in my head without tools because of the rule of seven[1]. Tool use is absolutely an intelligence amplifier but it isn't the same thing. > Because again,…

> I can write code that calculates the average letter frequency across any Wikipedia article. I can't do that in my head without tools because of the rule of seven

That is precisely the point I am trying to make. Its an arbitrary goalpost to say that knowing how to write the code doesnt mean its intelligent, and only doing it in a "chain of thought" would be.