Joel Z. Leibo

Joel Z Leibo

@jzleibo.bsky.social

Concordia was always an entity-compoment pattern. But it was improved in 2.0. Also, we realized that it was an important part of the story to emphasize and explain to anyone who didn't already know about it. So that's what we did in the 2.0 tech report.

Here:
arxiv.org/abs/2507.08892

Multi-Actor Generative Artificial Intelligence as a Game Engine

Generative AI can be used in multi-actor environments with purposes ranging from social science modeling to interactive narrative and AI evaluation. Supporting this diversity of use cases -- which we ...

arxiv.org

1 1

by Joel Z. Leibo

Joel Z Leibo

@jzleibo.bsky.social

Tutorial here: www.youtube.com/watch?v=2FO5...

Concordia Library v2.0 Release - Tutorial with Alexander (Sasha) Vezhnevets [Google DeepMind]

YouTube video by Cooperative AI Foundation

www.youtube.com

2

by Joel Z. Leibo

Joel Z Leibo

@jzleibo.bsky.social

Concordia 2.0: www.cooperativeai.com/post/google-...

Google DeepMind Releases Concordia Library v2.0

Google DeepMind has released Concordia v2.0, a platform providing a robust environment for creating multi-agent simulations, games, and AI evaluations.

www.cooperativeai.com

3 3 9

Reposted by: Joel Z. Leibo

by Joel Z. Leibo

Reposted by: Joel Z. Leibo

by Joel Z. Leibo

Reposted by: Joel Z. Leibo, Michael A. Shook

Reposted by: Joel Z. Leibo

Reposted by: Joel Z. Leibo, Anca Dragan

Reposted by: Joel Z. Leibo

Gillian Hadfield

@ghadfield.bsky.social

If you’ll be at #neurips this year, come to our tutorial on cross-disciplinary insights for AI alignment neurips.cc/virtual/2024...

NeurIPS Tutorial Cross-disciplinary insights into alignment in humans and machinesNeurIPS 2024

neurips.cc

1 9

Reposted by: Joel Z. Leibo

Aslan

@aslandizaji.bsky.social

Here is the code of the project:
github.com/aslansd/modi...
github.com/aslansd/modi...

Here is the paper of the project:
arxiv.org/abs/2411.17724

Incentives to Build Houses, Trade Houses, or Trade House Building Skills in Simulated Worlds under Various Governing Systems or Institutions: Comparing Multi-agent Reinforcement Learning to Generative...

It has been shown that social institutions impact human motivations to produce different behaviours, such as amount of working or specialisation in labor. With advancement in artificial intelligence (...

arxiv.org

2 1 6

Reposted by: Joel Z. Leibo

Tim Rocktäschel

@handle.invalid

Excited to reveal Genie 2, our most capable foundation world model that, given a single prompt image, can generate an endless variety of action-controllable, playable 3D worlds. Fantastic cross-team effort by the Open-Endedness Team and many other teams at Google DeepMind! 🧞

Jack Parker-Holder @jparkerholder.bsky.social · Dec 4

Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.

3 18 94

Reposted by: Joel Z. Leibo

Blake Richards

@tyrellturing.bsky.social

💯

Hallucination is totally the wrong word, implying it is perceiving the world incorrectly.

But it's generating false, plausible sounding statements. Confabulation is literally the perfect word.

So, let's all please start referring to any junk that an LLM makes up as "confabulations".

Cian O'Donnell @cianodonnell.bsky.social · Dec 11

petition to change the word describing ChatGPT's mistakes from 'hallucinations' to 'confabulations'

A hallucination is a false subjective sensory experience. ChatGPT doesn't have experiences!

It's just making up plausible-sounding bs, covering knowledge gaps. That's confabulation

18 45 210

Reposted by: Joel Z. Leibo

Ted Underwood

@tedunderwood.com

How did we end up in a world where 1) in Jupyter notebooks, "return" means add a line but "shift-return" means execute cell,

whereas 2) in prompt fields for LLMs, "shift-return" means add a line and "return" means execute this prompt.

trivial annoyance, but it's a Top 5 Trivial Annoyance

9 1 55

Reposted by: Joel Z. Leibo

Eugene Vinitsky 🍒

@eugenevinitsky.bsky.social

The multiagent LLM people are going to do me in. What do you mean you told one agent it was a manager and the other a worker and it slightly improved performance

7 2 42

Reposted by: Joel Z. Leibo

Murray Shanahan

@mpshanahan.bsky.social

However, a good explanation for much of the sophisticated behaviour we see in today's chatbots is that they are role-playing. 3/4

2 1 9

Reposted by: Joel Z. Leibo

by Joel Z. Leibo

Joel Z Leibo

@jzleibo.bsky.social

One can also explain human behavior this way, of course 😉, we are all role playing.

But I certainly agree with the advice you offer in this thread. Humans harm themselves when they stop playing roles that connect to other humans.

Murray Shanahan @mpshanahan.bsky.social · Jul 22

However, a good explanation for much of the sophisticated behaviour we see in today's chatbots is that they are role-playing. 3/4

4

by Demis Hassabis — Reposted by: Joel Z. Leibo, Ian Goodfellow

References

Fields & subjects