📢

How Do Selection Theorems Relate To Interpretability?

📅 2022
public awareness
⚪ Common
#ai #interpretability (ml & ai) #selection theorems

📖 Description

One pretty major problem with today's interpretability methods (e.g. work by [Chris Olah & co](https://transformer-circuits.pub/2021/framework/index.html)) is that we have to redo a bunch of work whenever a new net comes out, and even more work when a new architecture or data modality comes along (like e.g. transformers and language models).

📊 Game Impacts

Variable Change Condition
Research +5 Always
Ethics Risk -5 Always

💭 Reactions

🔬 Safety Researcher Reaction: ⚠️ Placeholder - Needs Real Quote
"Tangentially related to core safety concerns"
📰 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 (3) ai, interpretability (ml & ai), selection theorems → Suggest tag changes
📊 Game Impacts (2) 2 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