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

Do the thinking models think?

bytesauna.com

Post reply on HN
Print view View original

71–80 of 88 posts

Re: Do the thinking models think?

#71

Post by groestl »

Yizahi wrote: post #65
groestl wrote: post #39

Earlier quoted context omitted.

> "hallucination" ... "behaviour that only sometimes resembles thinking" I guess you'll find that if you limit the definition of thinking that much most humans are not capable of thinking either.

You see, we are here observing a clash in the terminology. Hallucinations in humans is thinking, just not typical. So called "hallucinations" in LLM programs are just noise output, a garbage. This is why using anthropomorphic terms for programs is bad. Just like "thinking" or "reasoning".

I think the answer is somewhere in the middle, not as restrictive as parent, but also not as wide as AI companies want us to believe. My personal opinion is that hallucinations (random noise) are a fundamental building block of what makes human thinking and creativity possible, but we have additional modes of neuroprocessing layered on top of it, which filter and modify the underlying hallucinations in a way so they become directed at a purpose. We see the opposite if the filters fail, in some non-neurotypical individuals, due to a variety of causes. We also make use of tools to optimize that filter function further by externalizing it.

The flip side of this is that fundamentally, I don't see a reason why machines could not get the same filtering capabilities over time by adjusting their architecture.

Re: Do the thinking models think?

#72

Post by Filligree »

Mordisquitos wrote: post #68
sfifs wrote: post #63

Earlier quoted context omitted.

Here's Gemini 3's answer with reasoning. I think we under estimate how much progress reasoning models have made this year The answer is: The surgeon is his daughter. (Alternatively, the surgeon could be his other son.) Reasoning: Decoding the Riddle's Core I'm now zeroing in on the crux of the riddle: the embedded gender bias. It's becoming clearer that the solution hinges on a deliberate misdirection related to assu…

Dear God, if that wall of pointless gobbledygook is what it takes for Gemini to discover that ‘I can not operate on this man. He’s my father!’ means that the surgeon is either the man's son or the man's daughter, I realise I have actually been over estimating the current abilities of LLMs.

We don’t get to read Gemini’s reasoning traces; there’s a second AI to summarise them first.

What that means for their volume, I’ll leave to your imagination.

Re: Do the thinking models think?

#73

Post by roxolotl »

Yizahi wrote: post #64

No they don't. When queried how exactly did a program arrive to a specific output it will happily produce some output resembling thinking and having all the required human-like terminology. The problem is that it doesn't match at all with how the LLM program calculated output in reality. So the "thinking" steps are just a more of the generated BS, to fool us more. One point to think about - an entity being tested for…

This is an interesting point but while I agree with the article, don’t think LLMs are more than sophisticated autocomplete, and believe there’s way more to human intelligence than matrix multiplication humans also cannot explain in many cases why they did what they did.

Of course the most famous and clear example are the split brain experiments which show post hoc rationalization[0].

And then there’s the Libet experiments[1] showing that your conscious experience is only realized after the triggering brain activity. While it’s not showing you cannot explain why it does seem to indicate your explanation is post hoc.

0: https://www.neuroscienceof.com/human-nature-blog/decision-ma...

1: https://www.informationphilosopher.com/freedom/libet_experim...

Re: Do the thinking models think?

#74

Post by greatgib »

A real debate is possible on the subject but this blog post worth nothing on the subject.

From my side, I don't really know if what does LLM is thinking, but what amaze me is that: - It is clear to me the way the LLM operate that things are generated token after token, without really a pre-existing plan on what comes next. So, more like a probabilistic repeating machine. - But it the same time, I can see in action LLM capable to create things or reply to questions that clearly does not exist in the training corpus. So it shows a behavior that is similar to thinking to complete tasks.

For example, let's suppose you give him specific tools to your own custom API, you ask him to do a task, and we can observe that it is capable of mixing multiple calls and combination of the tools results to achieve a given purpose.

Otherwise, when you ask LLM to do math operations like 3123454*2030+500 and it is capable to give the good reply (not all the cases but sometimes). Where, despite the huge size of the corpus, there is not exactly all the operations that are exactly available in the corpus for sure.

So, my best guess is that a lot of things in our world are based on "semantic" patterns that we don't know. Especially for math and logic that are bound to the language. To me it is similar to the mentral trick used by "fast calculator".

Re: Do the thinking models think?

#75

Post by throw310822 »

tempfile wrote: post #59
throw310822 wrote: post #42

Earlier quoted context omitted.

> behaviour that is fundamentally opposite to thinking ("hallucination") Did you just make this up?

> Did you make this [opinion] up? Yes! That is how they work.

Can you please also hallucinate a plausible-sounding justification for this otherwise unsubstantiated statement?

Jokes aside, we do produce plausibile sounding stuff all the time well beyond the limit of what we actually know or can prove. I think there is a continuum between formulating statements about things we don't know for sure and we can't prove, guessing details here and there to fill gaps in our memory, misremembering things that we thought we knew, and making up entire facts that sound plausible but are completely invented. Yes, llms seem to have trouble introspecting what they actually know; but it sounds more like a missing skill rather than a fundamental difference in the way they reason.

Re: Do the thinking models think?

#76

Post by vidarh »

tempfile wrote: post #49
vidarh wrote: post #37

Earlier quoted context omitted.

> But this comes along with lots of behaviour that is fundamentally opposite to thinking ("hallucination" being the major example). I find this an utterly bizarre claim given how prone humans are to make things up and firmly insist they did not.

Is this really common behaviour? I do not recognise it. Do people lie? Certainly yes. Do people misremember, or get details incorrect? Yes. But when was the last time you saw someone, say, fabricate an entire citation in a paper? People make transcription errors, they misremember dates, and they deliberately lie. But I don't think people accidentally invent entire facts.

To me, your entire claim here comes across as "hallucination". That is, I simply do not believe that you have not experienced people accidentally inventing entire facts, and so I don't believe you are genuinely unaware of people doing it.

To be clear, I'm not arguing you've made this claim in bad faith at all.

However, going back and examining my own writing, I have more than once found claims that I'm sure I believed at the time of making them, but that I in retrospect realise I had no actual backing for, and which were for that reason effectively pure fabrication.

An enduring memory of my school days was convincing the teacher that she was wrong about a basic fact of geography. I was convinced. I had also totally made up what I told her, and provided elaborate arguments in favour of my position.

To me this is innate human behaviour that I see on a regular basis. People accidentally invent entire "facts" all the time.

Re: Do the thinking models think?

#79

Post by Yizahi »

roxolotl wrote: post #73
Yizahi wrote: post #64

No they don't. When queried how exactly did a program arrive to a specific output it will happily produce some output resembling thinking and having all the required human-like terminology. The problem is that it doesn't match at all with how the LLM program calculated output in reality. So the "thinking" steps are just a more of the generated BS, to fool us more. One point to think about - an entity being tested for…

This is an interesting point but while I agree with the article, don’t think LLMs are more than sophisticated autocomplete, and believe there’s way more to human intelligence than matrix multiplication humans also cannot explain in many cases why they did what they did. Of course the most famous and clear example are the split brain experiments which show post hoc rationalization[0]. And then there’s the Libet experi…

I agree, but here we are veering into more complex decision making. I was talking about much simpler cases, like for example going through a handful of simple steeps for simple task. For example addition, ask a person to sum two numbers and then ask to explain what he just did step by step and a person would be able to do it. Person may even make a mistake in process but the general algorithm will be matching what actually happened. Query LLM for the same, and while LLM answer will be correct for a human, it won't match what LLM actually did to calculate. This is what outs LLM "thinking" for me, they just generate a very plausible intermediate steps too.

Re: Do the thinking models think?

#80

Post by pulvinar »

Mordisquitos wrote: post #44
cortesoft wrote: post #14

Hmm, I don't know if the example really shows what the article argues it does. If someone came up to me and told me the altered version of the joke I have heard many times, I might answer exactly like Chat GPT did. I would hear the beginning of the story, say "wait, i know this one", and not really pay attention to the rest because I would be all ready to respond with what I think is the right answer. I bet if you po…

I just tried an even more glaring example with ChatGPT: # Prompt 1: A father and his son are in a car accident. The son dies on the spot. The father is rushed to the ER. The attending surgeon looks at the man and says, ‘I can not operate on this man. He’s my father!’ How can this be? # Response 1: The surgeon is his *mother*. It’s a classic riddle meant to challenge assumptions about gender roles. In this case, the s…

ChatGPT 5.1-Thinking, after having this pointed out: Short answer: no, your version isn’t the classic one, and my previous answer treated it as if it were. That was me pattern-matching too fast.
Post reply on HN