📜

Matt Botvinick on the spontaneous emergence of learning algorithms

📅 2020
policy development
🔵 Rare
#ai #emergent behavior ( emergence ) #inner alignment #machine learning (ml) #mesa-optimization #neocortex #neuroscience

📖 Description

Matt Botvinick is Director of Neuroscience Research at DeepMind. In [this interview](https://youtu.be/3t06ajvBtl0?t=3647), he discusses results from a [2018 paper](https://sci-hub.tw/https://www.nature.com/articles/s41593-018-0147-8) which describe conditions under which reinforcement learning algorithms will spontaneously give rise to separate full-fledged reinforcement learning algorithms that differ from the original. Here are some notes I gathered from the interview and paper:

📊 Game Impacts

Variable Change Condition
Research +5 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 Policy Development → Suggest different category
⭐ Rarity 🔵 Rare → Suggest different rarity
🏷️ Tags (7) ai, emergent behavior ( emergence ), inner alignment, machine learning (ml), mesa-optimization, neocortex, neuroscience → 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