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

Microgpt

karpathy.github.io

Post reply on HN
Print view View original

141–150 of 354 posts

Re: Microgpt

#141

Post by geokon »

> What’s the deal with “hallucinations”? The model generates tokens by sampling from a probability distribution. It has no concept of truth, it only knows what sequences are statistically plausible given the training data.

Extremely naiive question.. but could LLM output be tagged with some kind of confidence score? Like if I'm asking an LLM some question does it have an internal metric for how confident it is in its output? LLM outputs seem inherently rarely of the form "I'm not really sure, but maybe this XXX" - but I always felt this is baked in the model somehow

Re: Microgpt

#142

Post by DavidSJ »

geokon wrote: post #141

> What’s the deal with “hallucinations”? The model generates tokens by sampling from a probability distribution. It has no concept of truth, it only knows what sequences are statistically plausible given the training data. Extremely naiive question.. but could LLM output be tagged with some kind of confidence score? Like if I'm asking an LLM some question does it have an internal metric for how confident it is in its…

Yes, the actual LLM returns a probability distribution, which gets sampled to produce output tokens.

[Edit: but to be clear, for a pretrained model this probability means "what's my estimate of the conditional probability of this token occurring in the pretraining dataset?", not "how likely is this statement to be true?" And for a post-trained model, the probability really has no simple interpretation other than "this is the probability that I will output this token in this situation".]

Re: Microgpt

#143

Post by podnami »

geokon wrote: post #141

> What’s the deal with “hallucinations”? The model generates tokens by sampling from a probability distribution. It has no concept of truth, it only knows what sequences are statistically plausible given the training data. Extremely naiive question.. but could LLM output be tagged with some kind of confidence score? Like if I'm asking an LLM some question does it have an internal metric for how confident it is in its…

I would assume this is from case to case, such as:

- How aligned has it been to “know” that something is true (eg ethical constraints)

- Statistical significance and just being able to corroborate one alternative in Its training data more strongly than another

- If it’s a web search related query, is the statement from original sources vs synthesised from say third party sources

But I’m just a layman and could be totally off here.

Re: Microgpt

#144

Post by TiredOfLife »

darkpicnic wrote: post #55
jimbokun wrote: post #47

It’s pretty staggering that a core algorithm simple enough to be expressed in 200 lines of Python can apparently be scaled up to achieve AGI. Yes with some extra tricks and tweaks. But the core ideas are all here.

LLMs won’t lead to AGI. Almost by definition, they can’t. The thought experiment I use constantly to explain this: Train an LLM on all human knowledge up to 1905 and see if it comes up with General Relativity. It won’t. We’ll need additional breakthroughs in AI.

> Train an LLM on all human knowledge up to 1905 and see if it comes up with General Relativity. It won’t.

Same thing is true for humans.

Re: Microgpt

#145

Post by podnami »

DavidSJ wrote: post #142
geokon wrote: post #141

> What’s the deal with “hallucinations”? The model generates tokens by sampling from a probability distribution. It has no concept of truth, it only knows what sequences are statistically plausible given the training data. Extremely naiive question.. but could LLM output be tagged with some kind of confidence score? Like if I'm asking an LLM some question does it have an internal metric for how confident it is in its…

Yes, the actual LLM returns a probability distribution, which gets sampled to produce output tokens. [Edit: but to be clear, for a pretrained model this probability means "what's my estimate of the conditional probability of this token occurring in the pretraining dataset?", not "how likely is this statement to be true?" And for a post-trained model, the probability really has no simple interpretation other than "thi…

What happens before the probability distribution? I’m assuming say alignment or other factors would influence it?

Re: Microgpt

#146

Post by Lionga »

geokon wrote: post #141

> What’s the deal with “hallucinations”? The model generates tokens by sampling from a probability distribution. It has no concept of truth, it only knows what sequences are statistically plausible given the training data. Extremely naiive question.. but could LLM output be tagged with some kind of confidence score? Like if I'm asking an LLM some question does it have an internal metric for how confident it is in its…

The LLM has an internal "confidence score" but that has NOTHING to do with how correct the answer is, only with how often the same words came together in training data.

E.g. getting two r's in strawberry could very well have a very high "confidence score" while a random but rare correct fact might have a very well a very low one.

In short: LLM have no concept, or even desire to produce of truth

Re: Microgpt

#147

Post by andy12_ »

geokon wrote: post #141

> What’s the deal with “hallucinations”? The model generates tokens by sampling from a probability distribution. It has no concept of truth, it only knows what sequences are statistically plausible given the training data. Extremely naiive question.. but could LLM output be tagged with some kind of confidence score? Like if I'm asking an LLM some question does it have an internal metric for how confident it is in its…

The model could report the confidence of its output distribution, but it isn't necessarily calibrated (that is, even if it tells you that it's 70% confident, it doesn't mean that it is right 70% of the time). Famously, pre-trained base models are calibrated, but they stop being calibrated when they are post-trained to be instruction-following chatbots [1].

Edit: There is also some other work that points out that chat models might not be calibrated at the token-level, but might be calibrated at the concept-level [2]. Which means that if you sample many answers, and group them by semantic similarity, that is also calibrated. The problem is that generating many answer and grouping them is more costly.

[1] https://arxiv.org/pdf/2303.08774 Figure 8

[2] https://arxiv.org/pdf/2511.04869 Figure 1.

Re: Microgpt

#148

Post by DavidSJ »

podnami wrote: post #145
DavidSJ wrote: post #142

Earlier quoted context omitted.

Yes, the actual LLM returns a probability distribution, which gets sampled to produce output tokens. [Edit: but to be clear, for a pretrained model this probability means "what's my estimate of the conditional probability of this token occurring in the pretraining dataset?", not "how likely is this statement to be true?" And for a post-trained model, the probability really has no simple interpretation other than "thi…

What happens before the probability distribution? I’m assuming say alignment or other factors would influence it?

In microgpt, there's no alignment. It's all pretraining (learning to predict the next token). But for production systems, models go through post-training, often with some sort of reinforcement learning which modifies the model so that it produces a different probability distribution over output tokens.

But the model "shape" and computation graph itself doesn't change as a result of post-training. All that changes is the weights in the matrices.

Re: Microgpt

#149

Post by nurettin »

xdennis wrote: post #116
darkpicnic wrote: post #55

Earlier quoted context omitted.

LLMs won’t lead to AGI. Almost by definition, they can’t. The thought experiment I use constantly to explain this: Train an LLM on all human knowledge up to 1905 and see if it comes up with General Relativity. It won’t. We’ll need additional breakthroughs in AI.

> Train an LLM on all human knowledge up to 1905 and see if it comes up with General Relativity. It won’t. AGI just means human level intelligence. I couldn't come up with General Relativity. That doesn't mean I don't have general intelligence. I don't understand why people are moving the goalposts.

> AGI just means human level intelligence.

It seems more like people haven't decided on what the goal post is. If AGI is just another human, that's pretty underwhelming. That's why people are imagining something that surpasses humans by heaps and bounds in terms of reasoning, leading to wondrous new discoveries.

Re: Microgpt

#150

Post by 0xEF »

harvey9 wrote: post #128
byang364 wrote: post #114

Earlier quoted context omitted.

Imagine the people on here spraying their AI takes everywhere while being this oblivious, the code is more or less a standard assignment in all Deep Learning courses. The "reasoning" is two matrix transformations based on how often words appear next to each other.

Quite a few people on here are neither math nor CS grads and some of us don't work in tech for our day jobs either.

Right. But HN, among other platforms, is full of users who will confidently run their mouths about something they don't fully understand while believing they do. I think the previous commenter was being too shy in pointing out that even exceptionally smart people sometimes forget where the limits of their own knowledge are, not to mention consider themselves immune to any propaganda that surrounds the subject at hand.
Post reply on HN