📜

Defining capability and alignment in gradient descent

📅 2020
policy development
🔵 Rare
#ai #inner alignment #mesa-optimization

📖 Description

This is the first post in a series where I'll explore AI alignment in a simplified setting: a neural network that's being trained by gradient descent. I'm choosing this setting because it involves a well-defined optimization process that has enough complexity to be interesting, but that's still understandable enough to make crisp mathematical statements about. As a result, it serves as a good starting point for rigorous thinking about alignment.

📊 Game Impacts

Variable Change Condition
Research +10 Always
Vibey Doom +5 Always
Ethics Risk -5 Always

💭 Reactions

🔬 Safety Researcher Reaction: ⚠️ Placeholder - Needs Real Quote
"Critical insights for the field"
📰 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 Policy Development → Suggest different category
⭐ Rarity 🔵 Rare → Suggest different rarity
🏷️ Tags (3) ai, inner alignment, mesa-optimization → Suggest tag changes
📊 Game Impacts (3) 3 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