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

Summarize Any Article as a Dialog Between Two People with Bing Chat

aidemos.info

Post reply on HN
Print view View original

21–30 of 67 posts

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#21

Post by basch »

IIAOPSW wrote: post #13

Based on my previous attempts with that other well noted LLM, I don't think these models are at all good at managing "theory of mind". They seem to not keep track very well of which parties are privy to which information, which parties are supposed to be pursuing certain conversational objectives, and generally which direction information is supposed to be flowing. It often trips over itself at the level of 2 parties…

LLMs will become components of larger systems.

They are an example of a situation where putting excess effort into a problem returns a plausible result, but from an efficiency and accuracy standpoint, parts of what they are accomplishing are better solved by simpler systems.

As they act as an interpreter, they should be able to identify when to hand off tasks to subroutines, and then reincorporate the result.

Just because LLMs can successfully output what they are doing, doesn't mean they are the best tool for the job. They are sort of like a CPU, good at generalist everything tasks, better when augmented with coprocessors.

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#22

Post by LesZedCB »

akio wrote: post #17
akio wrote: post #16

Earlier quoted context omitted.

GPT-4: ---- Jane: John, I can't believe you're just going to leave me here in the middle of nowhere! This is so typical of you! John: Typical of me? Jane, this is exactly what you signed up for! Adventure, remember? It's not my fault that you're suddenly having second thoughts. Jane: Second thoughts? This isn't about having second thoughts, John! This is about you always charging ahead without considering the consequ…

Now write a dialog between Mary and David discussing the dialog between Alice and Bob. ---- Mary: David, after listening to Alice and Bob's conversation, it seems to me that Alice is empathizing with John's intentions, while Bob is more focused on Jane's feelings. David: I see what you mean, Mary. But don't you think Bob was right to emphasize the importance of understanding Jane's perspective? John's actions had a c…

the fact this came from a "stochastic parrot" still blows my mind.

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#23

Post by flangola7 »

AshamedCaptain wrote: post #20
IIAOPSW wrote: post #13

Based on my previous attempts with that other well noted LLM, I don't think these models are at all good at managing "theory of mind". They seem to not keep track very well of which parties are privy to which information, which parties are supposed to be pursuing certain conversational objectives, and generally which direction information is supposed to be flowing. It often trips over itself at the level of 2 parties…

In my very first interaction with Bing's bot, I was asking some details about PC components, and e.g. it was common for bing to give back answers containing phrases like "as we tested in our previous article" (verbatim, even using the plural 1st person). It is obvious it is just parroting from the websites it scraped. PC hardware means benchmark results which means benchmark websites/blogs which means the "as we test…

There's a research paper floating around...

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#24

Post by akio »

LesZedCB wrote: post #22
akio wrote: post #17

Earlier quoted context omitted.

Now write a dialog between Mary and David discussing the dialog between Alice and Bob. ---- Mary: David, after listening to Alice and Bob's conversation, it seems to me that Alice is empathizing with John's intentions, while Bob is more focused on Jane's feelings. David: I see what you mean, Mary. But don't you think Bob was right to emphasize the importance of understanding Jane's perspective? John's actions had a c…

the fact this came from a "stochastic parrot" still blows my mind.

That is a clue that GPT-4 is not a stochastic parrot and does in fact possess an understanding of language and a model of the world.

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#26

Post by jjeaff »

AshamedCaptain wrote: post #20
IIAOPSW wrote: post #13

Based on my previous attempts with that other well noted LLM, I don't think these models are at all good at managing "theory of mind". They seem to not keep track very well of which parties are privy to which information, which parties are supposed to be pursuing certain conversational objectives, and generally which direction information is supposed to be flowing. It often trips over itself at the level of 2 parties…

In my very first interaction with Bing's bot, I was asking some details about PC components, and e.g. it was common for bing to give back answers containing phrases like "as we tested in our previous article" (verbatim, even using the plural 1st person). It is obvious it is just parroting from the websites it scraped. PC hardware means benchmark results which means benchmark websites/blogs which means the "as we test…

So, I certainly wouldn't ascribe any higher level thinking to these LLMs. But they do seem to have more capability than just regurgitating information. They have some logical thinking skills that I assume are not really emergent, but built into the system. For example, I was working on a configuration file for a somewhat new and esoteric firmware, so there isn't much info online about it. But I asked if a specific parameter could include more than one value and bing chat answered that it's assumption was no because it could find no mention anywhere of being able to use more than one value for that parameter. As far as I can tell, no one has answered a similar question anywhere online that it could have been regurgitating, so it seems to have deduced it.

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#27

Post by MuffinFlavored »

> browse https://electrek.co/2023/05/15/renewables-us-utility-scale-g... and make a summary

I've been waiting intently for ChatGPT to have this functionality. I think there's a waiting list? Do we have any ETA on when this functionality will be possible?

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#28

Post by frakt0x90 »

No opinion on the model or product itself, but I remember reading a very early math or physics book (think like Euclid's elements or Newton's Principia from Hawking's Anthologies) and the proofs were laid out as a dialog between 2 people being critical of each others arguments. I always thought that was awesome. The point of a proof is to convince its reader, and before a lot of formality was created, they were literally laid out as a dialog where one person tried to convince the other.

I found it an effective and engaging mechanism and use it in my own head all the time.

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#29

Post by aeadio »

frakt0x90 wrote: post #28

No opinion on the model or product itself, but I remember reading a very early math or physics book (think like Euclid's elements or Newton's Principia from Hawking's Anthologies) and the proofs were laid out as a dialog between 2 people being critical of each others arguments. I always thought that was awesome. The point of a proof is to convince its reader, and before a lot of formality was created, they were liter…

This method dates back to Socrates https://en.m.wikipedia.org/wiki/Socratic_dialogue

Re: Summarize Any Article as a Dialog Between Two People with Bing Chat

#30

Post by andsoitis »

jjeaff wrote: post #26
AshamedCaptain wrote: post #20

Earlier quoted context omitted.

In my very first interaction with Bing's bot, I was asking some details about PC components, and e.g. it was common for bing to give back answers containing phrases like "as we tested in our previous article" (verbatim, even using the plural 1st person). It is obvious it is just parroting from the websites it scraped. PC hardware means benchmark results which means benchmark websites/blogs which means the "as we test…

So, I certainly wouldn't ascribe any higher level thinking to these LLMs. But they do seem to have more capability than just regurgitating information. They have some logical thinking skills that I assume are not really emergent, but built into the system. For example, I was working on a configuration file for a somewhat new and esoteric firmware, so there isn't much info online about it. But I asked if a specific pa…

I would be careful to draw that conclusion. Not all information LLMs are trained on is accessible to the wide public (e.g. ChatGPT has training data from closed sources).

Regardless, If you share the details of your prompt, I’d be interested to see whether my Google-fu turns up information.

Post reply on HN