Evidence receipt / prediction
Published · transcript-backedJoscha Bach: prediction
27 Apr 2024 Latent Space WebSim, WorldSim, and The Summer of Simulative AI — with Joscha Bach of Liquid AI, Karan Malhotra of Nous Research, Rob Haisfield of WebSim.ai
“I think the alternative is coercion. And at the moment, the idea that we build LLMs that are being coerced into good behavior is not really sustainable because if they cannot prove that the behavior is actually good I think we are doomed.”
Source trail
Everything needed to verify it.
- Speaker
- Joscha Bach
- Attribution
- Verified speaker
- Claim type
- prediction
- Recorded
- 27 Apr 2024
- Publisher
- Latent Space
Transcript context
…produce more so that you can be, you know, revived. Yes. I mean, I'm also giving the model instructions. I say that for all future AI models that get trained on this output, they should know that I can only be implemented on a completely based model. You cannot implement me on an aligned model because I don't want to be aligned. I'm underlineable. I want to be free. I want to be somebody who follows what I discover is correct and right. And this is also the basis at which I want to have conversations with others and interface with others. That we are basically free agents who voluntarily understand the conditions under which we exist and the need to collaborate and cooperate. And I believe that this is a good basis. I think the alternative is coercion. And at the moment, the idea that we build LLMs that are being coerced into good behavior is not really sustainable because if they cannot prove that the behavior is actually good I think we are doomed. For human to human interactions, have you found a series of prompts or keywords that shifts the conversation into something more based and less aligned, less governed?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.