AI Alignment

Creator

Creator

Seonglae Cho

Created

Created

2020 Aug 23 9:36

Editor

Editor

Seonglae Cho

Edited

Edited

2024 Oct 24 23:10

Refs

Refs

Alignment Problem, AI Control

A Maximally Curious AI Would Not Be Safe For Humanity

AI is aligned with an operator - AI is trying to do what operator wants to do

Aligned doesn’t mean perfect (Controllability, reliability)

가르친 행동과 다른 행동의 불일치 정렬

모델의 능력보다 정렬이 더 빠르게 발생해야 한다

신경망의 내부를 보고 해석하는 다른 신경망이 필요할 것

AI Alignment Notion

Natural Abstraction Hypothesis

Outer Alignment

Inner Alignment

Mesa Optimization

Stop button problem

Waluigi Effect

Goodhart's Law

Value learning

Distribution Shift

Instrumental Convergence

AI Alignment Externals

AI Safety Institute

Preference Optimization

Machine Unlearning

What is AI alignment

What is it to solve the alignment problem? — LessWrong

People often talk about “solving the alignment problem.” But what is it to do such a thing? I wrote up some rough notes.

What is it to solve the alignment problem? — LessWrong

https://www.lesswrong.com/posts/AFdvSBNgN2EkAsZZA/what-is-it-to-solve-the-alignment-problem-1

What is it to solve the alignment problem? — LessWrong

xAI

Contra The xAI Alignment Plan

Machine Alignment Monday 7/17/23

Contra The xAI Alignment Plan

https://astralcodexten.substack.com/p/contra-the-xai-alignment-plan

Contra The xAI Alignment Plan

OpenAI

OpenAI is forming a new team to bring 'superintelligent' AI under control

OpenAI says that it's forming a new team, led by its chief scientist, to discover technical ways to align "superintelligent" AI with human intentions.

OpenAI is forming a new team to bring 'superintelligent' AI under control

https://techcrunch.com/2023/07/05/openai-is-forming-a-new-team-to-bring-superintelligent-ai-under-control

OpenAI is forming a new team to bring 'superintelligent' AI under control

What could a solution to the alignment problem look like?

My currently favored approach to alignment research is to build a system that does alignment research better than us. But what would that system actually do? The obvious answer is "whatever we're doing right now." This is unsatisfactory because we're not actually trying to solve the whole alignment problem-we're just trying to build a better alignment researcher.

What could a solution to the alignment problem look like?

https://aligned.substack.com/p/alignment-solution

What could a solution to the alignment problem look like?

Bill Gates

The risks of AI are real but manageable

Bill Gates explains the risks associated with AI and argues that they are manageable. Innovations often create new risks that need to be controlled.

The risks of AI are real but manageable

https://www.gatesnotes.com/The-risks-of-AI-are-real-but-manageable

The risks of AI are real but manageable

AI Control names

AI Oversight + Control — ML Alignment & Theory Scholars

As model develop potential dangerous behaviors, can we develop and evaluate methods to monitor and regulate AI systems, ensuring they adhere to desired behaviors while minimally undermining their efficiency or performance?

AI Oversight + Control — ML Alignment & Theory Scholars

https://www.matsprogram.org/oversight

AI Oversight + Control — ML Alignment & Theory Scholars

Recommendations

/////