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

Can language models serve as text-based world simulators?

arxiv.org

Post reply on HN
Print view View original

61–68 of 68 posts

Re: Can language models serve as text-based world simulators?

#61

Post by segmondy »

sbotzek wrote: post #15

I tried for a few months getting ChatGPT4 to work with a MUD. In my experience it's not very good at that particular task. One problem I ran into was its ability to logically connect rooms. In a MUD you navigate by going north, south, east, west, up, or down. Not every room lets you go any direction. And usually, if you go east, in your new room, you can go west. Rarely a level creator will make this not be true. Cha…

Looks more like a prompting and coding issue. ChatGPT4 is not strong AGI. It's an AGI, but you need to guide it.

Re: Can language models serve as text-based world simulators?

#62

Post by infotainment »

immibis wrote: post #58
lolinder wrote: post #57

Earlier quoted context omitted.

It's still running now: https://aidungeon.com/

Apparently still with a version of the NSFW filter that made everyone abandon it in 2020.

Really? I was under the impression that was an OpenAI limitation, which they eventually worked around by deploying their own models.

Re: Can language models serve as text-based world simulators?

#63

Post by catlifeonmars »

TeMPOraL wrote: post #43
catlifeonmars wrote: post #40

Earlier quoted context omitted.

Think about what the model is doing: It’s sampling from a statistical distribution of likely tokens, one of which is the correctly spelled variable name.

Yes. The presence of the correctly spelled name earlier in the context should've dominated the distribution so much that it should've been extremely unlikely to select an incorrectly spelled variable name in the place where the correct name should go.

What if the model got more training data? There’s no guarantee that the training data causes the model to converge on correctness. It’s not like this stuff is curated for specific problems.

Re: Can language models serve as text-based world simulators?

#64

Post by lolinder »

infotainment wrote: post #62
immibis wrote: post #58

Earlier quoted context omitted.

Apparently still with a version of the NSFW filter that made everyone abandon it in 2020.

Really? I was under the impression that was an OpenAI limitation, which they eventually worked around by deploying their own models.

It's both.

The game started as a side project that went crazy viral as the first real way people could access an LLM (GPT-2 at the time). That of course immediately led to people using it for NSFW content, and they were really the first project to have to deal with the question of what to do about that content. Their initial reaction was to deploy a filter, which worked but was unpopular with many in their early audience.

I haven't followed the project for a while, but my understanding was that they rolled back the filter at least for paid accounts. But when they had the filter it wasn't just an OpenAI restriction because their filter actually predated GPT-3 and OpenAI's APIs.

Re: Can language models serve as text-based world simulators?

#65

Post by skybrian »

crooked-v wrote: post #51
skybrian wrote: post #6

Maybe they can, but they’re trained on conversation and stories (among other things) rather than simulations. These are more general than the log of a simulation run in how they use time. Stories can be chronological, but they can also fill in the details in any order using things like flashbacks. Or they can get really complicated with time travel stories. So it seems like to understand a story well, an LLM would ne…

Now I wonder what one would get from an LLM trained entirely on several bajillion text logs of people playing text games like Zork.

Yeah, might be interesting. I think it wouldn’t be too hard to generate training runs automatically, especially given a solution to start from.

Re: Can language models serve as text-based world simulators?

#66

Post by immibis »

lolinder wrote: post #64
infotainment wrote: post #62

Earlier quoted context omitted.

Really? I was under the impression that was an OpenAI limitation, which they eventually worked around by deploying their own models.

It's both. The game started as a side project that went crazy viral as the first real way people could access an LLM (GPT-2 at the time). That of course immediately led to people using it for NSFW content, and they were really the first project to have to deal with the question of what to do about that content. Their initial reaction was to deploy a filter, which worked but was unpopular with many in their early audi…

"worked" as in "made OpenAI happy" but not as in "retained their customers". People were getting banned for using words like "melon" (racist implication, said the filter).

Re: Can language models serve as text-based world simulators?

#67

Post by motbus3 »

Folcon wrote: post #25
danjc wrote: post #18

Earlier quoted context omitted.

Somewhat related, Yann LeCun posted a few months back about how many concepts aren't understood through language and therefore can't be modeled through it (which is why LLM's are terrible with things like position and direction). https://x.com/ylecun/status/1768353714794901530?s=46

To people who claim that "thinking and reasoning require language", here is a problem: Imagine standing at the North Pole of the Earth. Walk in any direction, in a straight line, for 1 km. Now turn 90 degrees to the left. Walk for as long as it takes to pass your starting point. Have you walked: 1. More than 2xPi km 2. Exactly 2xPi km 3. Less than 2xPi km 4. I never came close to my starting point. Think about how yo…

I think the problem the author is putting is that it does not have any reasoning behind. It is a sheer coincidence it works eventually for problems that requires logic. Mostly it could be because the dataset increases chances of it being right and not because it did process anything
Post reply on HN