📢

TASP Ep 3 - Optimal Policies Tend to Seek Power

📅 2021
public awareness
⚪ Common
#ai #instrumental convergence

📖 Description

Welcome to the Technical AI Safety Podcast, the show where I interview computer scientists about their papers. This month I covered [Optimal Policies Tend to Seek Power](https://arxiv.org/abs/1912.01683v6), which is closely related to [Seeking Power is Often Robustly Instrumental in MDPs](https://www.lesswrong.com/posts/6DuJxY8X45Sco4bS2/seeking-power-is-often-robustly-instrumental-in-mdps) which is a part of the [Reframing Impact](https://www.lesswrong.com/s/7CdoznhJaLEKHwvJW) sequence and was recently a part of the [2019 review](https://www.lesswrong.com/posts/kdGSTBj3NA2Go3XaE/2019-review-voting-results).

📊 Game Impacts

Variable Change Condition
Research +5 Always

💭 Reactions

🔬 Safety Researcher Reaction: ⚠️ Placeholder - Needs Real Quote
"Provides general AI context"
📰 Media Reaction: ⚠️ Placeholder - Needs Real Quote
"Discussed in AI safety community"
💡 Found a Real Quote? Suggest it here

🔗 Sources

🏷️ Event Metadata

Think this event's metadata could be improved? Suggest changes to category, rarity, tags, game impacts, or p(doom) effects.

📁 Category Public Awareness → Suggest different category
⭐ Rarity ⚪ Common → Suggest different rarity
🏷️ Tags (2) ai, instrumental convergence → Suggest tag changes
📊 Game Impacts (1) 1 variable changes → Suggest impact changes
☢️ p(Doom) Impact No direct impact → Suggest p(doom) change
📝 General Metadata Year, description, reactions → Comprehensive review

🤝 Found an Issue?

This event data is sourced from the pdoom-data repository. If you notice errors or want to suggest improvements:

GitHub Issue (Preferred) 📧 Email (No GitHub)
← Back to All Events