Oly on AI
Subscribe
Sign in
Home
AI Governance
Research
Fun
Oly
Archive
Research
Cooperation and Alignment in Delegation Games
You need both! (and also fairness)
Nov 15, 2023
•
Oliver Sourbut
1
Share this post
Oly on AI
Cooperation and Alignment in Delegation Games
Copy link
Facebook
Email
Notes
More
Deliberation Everywhere: Simple Examples
We previously discussed a conceptual algorithmic breakdown of some aspects of goal-directed behaviour with the intention of inspiring…
Jun 27, 2022
•
Oliver Sourbut
Share this post
Oly on AI
Deliberation Everywhere: Simple Examples
Copy link
Facebook
Email
Notes
More
Deliberation, Reactions, and Control
Tentative Definitions and a Restatement of Instrumental Convergence
Jun 27, 2022
•
Oliver Sourbut
Share this post
Oly on AI
Deliberation, Reactions, and Control
Copy link
Facebook
Email
Notes
More
Breaking Down Goal-Directed Behaviour
When we speak about entities ‘wanting’ things, or having ‘goal-directed behaviour’, what do we mean?
Jun 16, 2022
•
Oliver Sourbut
Share this post
Oly on AI
Breaking Down Goal-Directed Behaviour
Copy link
Facebook
Email
Notes
More
Conditions for mathematical equivalence of Stochastic Gradient Descent and Natural Selection
Analogies are often drawn between natural selection and gradient descent (and other training procedures for parametric algorithms). It…
May 9, 2022
•
Oliver Sourbut
1
Share this post
Oly on AI
Conditions for mathematical equivalence of Stochastic Gradient Descent and Natural Selection
Copy link
Facebook
Email
Notes
More
Some real examples of gradient hacking
Speculation and an invitation to make further suggestions or clarifications
Nov 22, 2021
•
Oliver Sourbut
Share this post
Oly on AI
Some real examples of gradient hacking
Copy link
Facebook
Email
Notes
More
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts