Welcome to the alpha release of TYPE III AUDIO.
Expect very rough edges and very broken stuff—and regular improvements. Please share your thoughts.
PodcastsAI Safety Fundamentals: Alignment[Week 7] “Progress on Causal Influence Diagrams” by Everitt et al
“Progress on Causal Influence Diagrams” by Everitt et al
13 May 2023 · AI Safety Fundamentals: Alignment
AI Safety Fundamentals: Alignment
Readings from the AI Safety Fundamentals: Alignment course.
Subscribe:
By Tom Everitt, Ryan Carey, Lewis Hammond, James Fox, Eric Langlois, and Shane Legg
About 2 years ago, we released the first few papers on understanding agent incentives using causal influence diagrams. This blog post will summarize progress made since then. What are causal influence diagrams? A key problem in AI alignment is understanding agent incentives. Concerns have been raised that agents may be incentivized to avoid correction, manipulate users, or inappropriately influence their learning. This is particularly worrying as training schemes often shape incentives in subtle and surprising ways. For these reasons, we’re developing a formal theory of incentives based on causal influence diagrams (CIDs).
Source:
https://deepmindsafetyresearch.medium.com/progress-on-causal-influence-diagrams-a7a32180b0d1
Narrated for AI Safety Fundamentals by TYPE III AUDIO.
---
