[Xx_crazy420_xX]

I think open-ended simulation for agents will be a key component for training and planning. Similar as human dreams simulate different scenarios in our head. Biggest challenge will be simulating more abstract and complex systems.

Few months ago I did experiment with an open-ended world simulation for AI agent, where the simulated world was progressively building itself based on each of agent actions in open-ended manner. The idea was to give an agent infinite possibility regarding tool calling, where the tool call would be approved by the adjudicator, and the world state would change. The key issues with the PoC were:

  - World decoherence (tried to solve that with a poor graph implementation)
  - World flatness - high abstraction did not account for small events that would compound in real world
  - Start with empty context was real issue to get the agent to explore the world
  

Anyways the project came to be really funny when you watched agent struggling in desperation to perform real world actions which would be impossible in real world. Main observation was that when presented agent with current action budget, it modulated the creativity and how desperate its actions were.

[avaer]

I agree; after running out of data on the internet, and humans being too slow to generate data, simulation is the only frontier left for improving things (training, datasets, reasoning). And it's probably the most ethical one too.

If nothing else I'm glad to see "world models" that are actually modeling some kind of worlds, instead of the term being applied as a hype layer for video/splats diffusion.

[Xx_crazy420_xX]

Physical simulations seem like next step, but how do you simulate dynamics in complex systems im not sure. Stock market is a good example with many trying to simulate that, but at the end you have to make some tradeoffs in terms of abstraction level you are simulating.

For social backed simulations i guess some kind of grounding will be needed based on real examples, but then the out of distribution cases will need an other solution. As rate of changes in our civilization increases, the out of distribution cases will be more and more prominent.

[dofm]

Is there much evidence we use dreams to pre-emptively simulate scenarios?

Dreaming seems much more likely to be neurological tidying and emotional reprocessing. Helpful for identifying and surfacing long term subconscious needs but not for planning.

My dreams would be precisely useless for making plans from, unless those plans were to involve being caught in public wrapped only in a towel. And even then, I'm not sure they'd be particularly helpful.

[algoth1]

There’s an hypothesis that states we dream so we don’t lose visual processing neural connections. Similar to what happens in blind people: visual processing neurons are recruited to other sensory tasks due to lack of stimulation. My ed. guess is that dreaming probably serves multiple purposes

[dofm]

There was an early visual neural network demonstration — strong feeling it was called "Yorick" or somesuch as it was built in a plaster skull — that had a square grid of red LEDs to show its output state as a simple picture; when its camera was unplugged the neural network appeared to "dream" in the sense that things it had seen would flicker and swirl in the output.

I saw this in a video in the early 90s and cannot remember where.

[Xx_crazy420_xX]

I agree, for me it dreaming was always reprocessing. The resimulation of scenarios part i mentioned can be over-assumption and it might be wrong. One thing i noticed is that sometimes i reprocess motoric movements after martial arts lessons, that was my main clue.

[dofm]

Right — I mean, I think it's interesting what "dream" means colloquially.

Like, we "dream up" things, or we "have dreams" (underspecified broad ideals for our best life etc.)

I do wonder if sometimes reprocessing dreams has helped me have a better response for something when it reoccurs — like, how to better respond to being slighted or abused or sometimes even complimented.

But I don't know if those could be said to be "plans" on any level. It's a kind of training, though.

Dreaming does help you train for grief and loss, I think.

And sometimes for me it has encapsulated the wisdom or reassurance of someone I have lost; my father appears to be quite involved in my recovery from burnout and my imagining a better life for myself and he died several years ago.

[walrus01]

Out of curiosity would you be willing to share the full system prompt for the agent in question described in this test?

[Xx_crazy420_xX]

sure: https://github.com/Srakai/bench-evolve/blob/76677b5066bafbab...

[mark_l_watson]

Thanks, interesting. Two years ago I wrote a text adventure game that used a LLM model. The system was very simple, but still was interesting. A friend of mine, Ben Goertzel, has been interesting in games/VR for a long while.

I wrote a book on the subject, but now really old material: AI Agents in Virtual Reality Worlds — J. Wiley, 1996

[Xx_crazy420_xX]

I'm a huge fan of Ben. Have been tracking the OpenCog initiative for some itmem and think that moving concepts from latentspace to atomspace is best way to efficiently merge our current digital information infrastructure with LLM knowledge.

Regarding your book, I'm shocked that 'AI Agent' concept predates me. Have not read your book, but i think it would be interesting to compare your perspective with today's building blocks which were not available for that time.