📢

Does SGD Produce Deceptive Alignment?

📅 2020
public awareness
🔵 Rare
#ai #deceptive alignment #distillation & pedagogy #inner alignment #machine learning (ml) #mesa-optimization

📖 Description

[Deceptive alignment](https://www.lesswrong.com/posts/zthDPAjh9w6Ytbeks/deceptive-alignment) was first introduced in [Risks from Learned Optimization](https://www.lesswrong.com/s/r9tYkB2a8Fp4DN8yB), which contained initial versions of the arguments discussed here. Additional arguments were discovered in [this episode](https://futureoflife.org/2020/07/01/evan-hubinger-on-inner-alignment-outer-alignment-and-proposals-for-building-safe-advanced-ai/) of the AI Alignment Podcast and in conversation with Evan Hubinger.

📊 Game Impacts

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

💭 Reactions

🔬 Safety Researcher Reaction: ⚠️ Placeholder - Needs Real Quote
"This is a significant contribution to alignment research"
📰 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 🔵 Rare → Suggest different rarity
🏷️ Tags (6) ai, deceptive alignment, distillation & pedagogy, inner alignment, machine learning (ml), 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