aisafety.info, the Table of Content
Here is a list of Q&A from https://aisafety.info/ . When I discovered the site, I was impressed by the volume of material produced. However, the interface is optimized for beginners. The following table of contents is for individuals who wish to navigate the various sections more freely. It was constructed by clustering the Q&A into subtopics. I’m not involved with aisafety.info, I just want to increase the visibility of the content they produced by presenting it in a different way. They are also working on a new interface. This table can also be found https://aisafety.info/toc/.
🆕 New to AI safety? Start here.
📘 Introduction to AI Safety
🧠 Introduction to ML
🤖 Types of AI
What is “narrow AI”? & What is artificial general intelligence (AGI)?
What are the differences between AGI, transformative AI, and superintelligence?
🚀 Takeoff & Intelligence explosion
Takeoff
Intelligence explosion
What are the differences between a singularity, an intelligence explosion, and a hard takeoff?
📅 Timelines
Expert surveys
Is Compute and Scaling enough?
From AGI to ASI
❗ Types of Risks
How might things go wrong with AI even without an agentic superintelligence?
Is large-scale automated AI persuasion and propaganda a serious concern?
🔍 What would an AGI be able to do?
Basic capabilities
Advanced capabilities
Strategic implications
🌋 Technical source of unalignment
Orthogonality thesis
Specification Gaming
Goal Misgeneralization
Outer and Inner alignment
🎉 Current prosaic solutions
🗺️ Strategy
Win conditions
Race dynamics
All things considered
Impact of AI Safety
💭 Consciousness
❓ Not convinced? Explore the arguments.
🤨 Superintelligence is unlikely?
😌 Superintelligence won’t be a big change?
⚠️ Superintelligence won’t be risky?
Are there any detailed example stories of what unaligned AGI would look like?
Any AI will be a computer program. Why wouldn’t it just do what it’s programmed to do?
Wouldn’t AIs need to have a power-seeking drive to pose a serious risk?
Won’t humans be able to beat an unaligned AI since we have a huge advantage in numbers?
Wouldn’t a superintelligence be wise?
🤔 Why not just?
Why can’t we just turn the AI off if it starts to misbehave?
Why can’t we just “put the AI in a box” so that it can’t influence the outside world?
Can’t we limit damage from AI systems in the same ways we limit damage from companies?
🧐 Isn’t the real concern…
📜 I have certain philosophical beliefs, so this is not an issue
If I only care about helping people alive today, does AI safety still matter?
Why should someone who is religious worry about AI existential risk?
Does the importance of AI risk depend on caring about transhumanist utopias?
Is AI safety about systems becoming malevolent or conscious and turning on us?
We’re going to merge with the machines so this will never be a problem, right?
Aren’t AI existential risk concerns just an example of Pascal’s mugging?
🔍 Want to understand the research? Dive deeper.
💻 Prosaic alignment
Scalable oversight
Interpretability
Conceptual advances
Brain like AGI
📝 Agent foundation
Important concepts
Decision theory
Research directions
🏛️ Governance
Would a slowdown in AI capabilities development decrease existential risk?
What might an international treaty on the development of AGI look like?
🔬 Research Organisations
Overviews
Prosaic
Big labs
Academic labs
Other Orgs
Agent Foundation
Other
🤝 Want to help with AI safety? Get involved!
📌 General
📢 Outreach
What links are especially valuable to share on social media or other contexts?
How can I work on AGI safety outreach in academia and among experts?
🧪 Research
📚 Education and Career Path
📋 Guidance and Mentorship
🧪 Projects and Involvement
I’d like to do experimental work (i.e. ML, coding) for AI alignment. What should I do?
How can I do conceptual, mathematical, or philosophical work on AI alignment?
How can I use a background in the social sciences to help with AI alignment?
How can I do machine learning programming work to help with AI alignment?
What should I do with my machine learning research idea for AI alignment?
What should I do with my idea for helping with AI alignment?
🏛️ Governance
🛠️ Ops & Meta
How can I work on helping AI alignment researchers be more effective, e.g. as a coach?
How can I work on assessing AI alignment projects and distributing grants?
How can I do organizational or operations work around AI alignment?
With a quick test, I find their chat interface prototype experience quite satisfying.