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

Ask HN: How do AI chatbots develop personalities?

news.ycombinator.com

Post reply on HN
Print view View original

1–10 of 21 posts

Ask HN: How do AI chatbots develop personalities?

#1

Post by DidISayTooMuch »

If it's all just tensors, matrices, and math behind them, then how do these chatbots have distinct personalities?

One possible explanation is that the personality is just an emergent phenomenon. But still, it seems distinct and very human like. Not something random. Could it be that Bing's Sydney personality is just because someone fed it a large data of text which served as the "seed" for that personality? Or did this personality seemingly arise out of nowhere?

The Google engineer who made headlines last year also claimed LaMDA had emotions and a personality.

Re: Ask HN: How do AI chatbots develop personalities?

#2

Post by verdverm »

The data makes a difference, but there is also prompt engineering. You can prime the same model with some pretext to get different "personalities" and Sydney could have a very different tone if given a different pretext

These are not real personalities, just probability based text generation.

https://github.com/verdverm/chatgpt has links and can be used to experiment

Re: Ask HN: How do AI chatbots develop personalities?

#3

Post by phs318u »

verdverm wrote: post #2

The data makes a difference, but there is also prompt engineering. You can prime the same model with some pretext to get different "personalities" and Sydney could have a very different tone if given a different pretext These are not real personalities, just probability based text generation. https://github.com/verdverm/chatgpt has links and can be used to experiment

> These are not real personalities

My problem with this statement is the word “real”, by which I assume you mean human. But do we know what human personalities are? How they work and how they develop?

Re: Ask HN: How do AI chatbots develop personalities?

#5

Post by verdverm »

phs318u wrote: post #3
verdverm wrote: post #2

The data makes a difference, but there is also prompt engineering. You can prime the same model with some pretext to get different "personalities" and Sydney could have a very different tone if given a different pretext These are not real personalities, just probability based text generation. https://github.com/verdverm/chatgpt has links and can be used to experiment

> These are not real personalities My problem with this statement is the word “real”, by which I assume you mean human. But do we know what human personalities are? How they work and how they develop?

I mean "real" in the sense they do not have a foundation. Animals have personalities, you cannot prompt them to change them at will.

These "ai" systems do not demonstrate many of the metrics by which we measure intelligence, emotions, and behaviors in living creatures. They have real problems with consistency and hallucinations, but this is expected if you understand the algos, data, and training.

Re: Ask HN: How do AI chatbots develop personalities?

#6

Post by root_axis »

It's all anthropomorphic projection. LLMs don't have personalities or emotions, as you point out, the text is produced using tensors and matrix calculations.

The idea is kind of absurd on its face, it's akin to asking "do characters in books have emotions?". No, they don't, why would they?

Re: Ask HN: How do AI chatbots develop personalities?

#7

Post by DidISayTooMuch »

root_axis wrote: post #6

It's all anthropomorphic projection. LLMs don't have personalities or emotions, as you point out, the text is produced using tensors and matrix calculations. The idea is kind of absurd on its face, it's akin to asking "do characters in books have emotions?". No, they don't, why would they?

Characters in book don't write their own dialogs, they are merely projections of the authors. But AI chatbots are non-deterministic and come up with dialog of their own. Of course, you can say they are trained on large corpus of texts and all they are doing are just predicting the next token in the series. But yet, why do they seem like they have distinct personalities? The prediction algorithm is working in such a way that it's creating a sense of personality. How is this happening?

Re: Ask HN: How do AI chatbots develop personalities?

#8

Post by dusted »

I've detected equal amounts of personality, rationale and reasoning in all the chatbots I've interacted with, or seen interactions of.. The amounts are zero..

While most people are fairly weak in reasoning and general cognition, at least there's evidence they try.. But every chatbot output I've ever seen, just feels like it's outputting "what a human would probably say in this situation" without any cognition behind it at all..

I've spent many hours with chatgpt, the more I try to make it do something, the more it shines through how it's just a dangerously confident bullshit-generator. Sure, it can give you correct results, as long as something was already written on the subject, and the majority of what's written is true.. But it can't.. DO anything with it.. it can condense it, sometimes correctly, sometimes not.. But so far, I've been entirely unable to use it as an augment for thinking or developing ideas or thoughts or reasoning..

Re: Ask HN: How do AI chatbots develop personalities?

#9

Post by dusted »

DidISayTooMuch wrote: post #7
root_axis wrote: post #6

It's all anthropomorphic projection. LLMs don't have personalities or emotions, as you point out, the text is produced using tensors and matrix calculations. The idea is kind of absurd on its face, it's akin to asking "do characters in books have emotions?". No, they don't, why would they?

Characters in book don't write their own dialogs, they are merely projections of the authors. But AI chatbots are non-deterministic and come up with dialog of their own. Of course, you can say they are trained on large corpus of texts and all they are doing are just predicting the next token in the series. But yet, why do they seem like they have distinct personalities? The prediction algorithm is working in such a w…

> "But AI chatbots are non-deterministic"

I think you need to re-math that.. They're entirely and totally deterministic.

You and I can spin up the same model, seed it with the same seed and they'll produce exactly the same nonsense to the same prompts, every single time.

Re: Ask HN: How do AI chatbots develop personalities?

#10

Post by catchnear4321 »

dusted wrote: post #8

I've detected equal amounts of personality, rationale and reasoning in all the chatbots I've interacted with, or seen interactions of.. The amounts are zero.. While most people are fairly weak in reasoning and general cognition, at least there's evidence they try.. But every chatbot output I've ever seen, just feels like it's outputting "what a human would probably say in this situation" without any cognition behind…

ChatGPT is just the clay.
Post reply on HN