World Models · HackerPapers discussions

World Models — mentioned by xnx

Fri, 06 Feb 2026 18:33:17 GMT

> Suddenly all this focus on world models by Deep mind starts to make sense Google's been thinking about world models since at least 2018: https://arxiv.org/abs/1803.10122

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by SequoiaHope

Thu, 29 Jan 2026 19:17:40 GMT

Didn’t the original world models paper do some training in latent space? (Edit: yes[1]) I think robots imagining the next step (in latent space) will be useful. It’s useful for people. A great way to validate that a robot is properly imagining the future is to make that latent space renderable in pixels. [1] “By using features extracted from the world model as inputs to an agent, we can train a very compact and simple policy that can solve the required task. We can even train our agent entirely inside of its own hallucinated dream generated by its world model, and transfer this policy back…

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by esrh

Wed, 03 Sep 2025 09:14:43 GMT

They also don't mention the famous paper by Ha & Schmidhuber (https://arxiv.org/abs/1803.10122). The worst part is that they namedrop many other tangentially related and/or outright fraudulent "ai experts" like Hinton, Bengio, and LeCun.

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by d110af5ccf

Mon, 06 Feb 2023 02:08:10 GMT

> it seems that this merely exposes the normal operation. Insufficient images of that person prevented it from abstracting the person components from the background yes my point was that this total failure to abstract (or slice or average or whatever it is that it usually seems to do) appears to me to be neither the intended nor typical mode of operation > children under 1/10 of that age, who have seen only 10% of those images would not make the same kinds of mistakes but then children aren't being fed a stream of unrelated images. they're receiving a wide array of real time sensory input…

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by d110af5ccf

Tue, 27 Jul 2021 07:15:55 GMT

Your description kind of reminds me of the 2018 World Models publication. Are you familiar with that work and/or am I off base? (https://worldmodels.github.io/) (https://arxiv.org/abs/1803.10122)

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by candiodari

Fri, 11 Jun 2021 12:35:31 GMT

That may be true, but that's not to simulate. "Dreaming" is used to "simulate", and it's only a hack, in humans probably not even explicitly programmed. The hack is to have the simulator itself ... also be a learned system, and not to simulate the world, because you don't act on the real world, only a tiny part of it that you can measure and actually get into your brain (which is a simplified version of what you see, or a "latent variable"). There's no need to simulate anything that doesn't affect your reasoning. The information flows in reality with an intelligent actor is like this. World…

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by nmca

Sat, 23 Nov 2019 14:28:15 GMT

That seems a fairly specific meaning of the term that may not be in wider use, see eg: https://arxiv.org/abs/1803.10122

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by TaylorAlexander

Fri, 13 Jul 2018 06:40:34 GMT

Not a book but if you’re ML curious, I enjoyed reading the World Models paper. It was the first ML paper I read all the way through, and I found it approachable but still technically informative. I later learned the author has been in the AI game for decades, which explains his clear explanations and comfort with the material. PDF link at this page: https://arxiv.org/abs/1803.10122 The interactive web page explains what you’d be reading about: https://worldmodels.github.io/

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by baylearn

Thu, 28 Jun 2018 23:54:43 GMT

Background information about Reservoir Computing: https://en.wikipedia.org/wiki/Reservoir_computing World Models paper: https://arxiv.org/pdf/1803.10122.pdf https://worldmodels.github.io Previous HN Discussion: https://news.ycombinator.com/item?id=16860247 https://news.ycombinator.com/item?id=16860247

Paper and discussion history. A mention is not an endorsement.

World Models — HN submission

Sun, 03 Jun 2018 18:35:47 GMT

World Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

World Models — mentioned by hardmaru

Tue, 17 Apr 2018 21:46:50 GMT

Hi, I'm one of the authors of this paper (https://arxiv.org/abs/1803.10122, https://worldmodels.github.io). Happy to answer any questions you may have.

Paper and discussion history. A mention is not an endorsement.

World Models — mentioned by wei_jok

Wed, 28 Mar 2018 00:52:40 GMT

Link to the neural net generated Doom level demo: https://worldmodels.github.io/doomrnn/ Original article: https://worldmodels.github.io/ PDF version of the paper: https://arxiv.org/abs/1803.10122

Paper and discussion history. A mention is not an endorsement.