/explore
|
You are here 
|
www.lesswrong.com | ||
| | | | |
www.greaterwrong.com
In the post introducing mesa optimization, the authors defined an optimizer as The paper continues by defining a mesa optimizer as an optimizer that was selected by a base optimizer. However, there are a number of issues with this definition, as some have already pointed out. First, I think by this definition humans are clearly not mesa optimizers. Most optimization we do is implicit. Yet, humans are the supposed to be the prototypical examples of mesa optimizers, which appears be a contradiction. |
|
| | | | | ||
| | | | |
www.alignmentforum.org
Preface The following text is my submission for theAI Safety Public Materials contest. In it, I try to lay out the importance of AI Safety Research... |
|
| | | | | ||
| | | | |
www.alignmentforum.org
AI researchers warn that advanced machine learning systems may develop their own internal goals that don't match what we intended. This "mesa-optimiz... |
|
| | | | | ||
| | | | |
status451.com
"He wrote this post, and then people were hurt. There appears to be no rational evaluation of how or why this happened. No consideration of other factors in play, and no meaningful allowance for any alternative explanations." Normally I'd feel like writing this on the blog would be gauche. Believe it or not, I am... |
|
| | | |||
