Posts

Clifford Algebra and SageMath Tutorial

Kernel: SageMath 10.2Clifford Algebra TutorialThis notebook is a tutorial on how to use Clifford Algebras and SageMath. To run it, you will need either a local sage executable, or to run it on cocalc.
Last updated on Jan 1, 2024 12 min read

Deep Dream for Transformers

GPT2 Visualization GPT2 Model Structure
Aug 1, 2023 1 min read

Joint Text-EEG Embeddings

Here is a proposal I pitched to the Emotiv EEG company, since they have a bunch of EEG data and infrastructure to pay customers to help with distributed data collection. They were interested but we ended up stopping short of having me work there for the summer.
Jun 24, 2023 10 min read

Democratic AI Constitution: Round-Robin Debate and Synthesis

In this document, we propose a comprehensive and dynamic approach to address the challenges of creating a democratic constitution for AI systems. Recognizing the diversity and complexities of various demographic, political, and philosophical groups, our approach involves generating group-specific constitutions using OpenAI’s GPT-4 model.
Jun 13, 2023 7 min read

Nature < Nurture for AIs

Let’s imagine a hypothetical scenario where an AI is somehow trained in a way that is analogous to a human childhood in all of the relevant ways. Maybe it has a loving mother and family, maybe it has to learn to play well with peers, and maybe it has to learn to integrate into a larger social context.
Jun 4, 2023 9 min read

Conversationism

Crossposted at https://www.lesswrong.com/posts/HpHyERTmsmhDiRHtY/conversationism. Intro There seems to be a stark contrast between my alignment research on ontology maps and on cyborgism via Neuralink. I claim that the path has consisted of a series of forced moves, and that my approach to the second follows from my conclusions about the first.
Feb 27, 2023 17 min read

Be the Agi

Crossposted at https://www.lesswrong.com/posts/FnfAnsAH6dva3kCHS/research-direction-be-the-agi-you-want-to-see-in-the-world. Be the AGI you want to see in the world. Epistemic status: highly speculative, authors are not neuroscientists. Summary It may be possible to enhance human intelligence via a brain-computer interface (BCI).
Feb 4, 2023 11 min read

Repls and Elk

Crossposted at https://www.lesswrong.com/posts/C5PZNi5fueH2RC6aF/repl-s-and-elk. In my previous post I talked about read-eval-print loops as providing a type signature for agents. I will now explain how you can quickly transition from this framework to an ELK solution.
Last updated on Feb 16, 2023 3 min read

Repls

Cross-posted at https://www.lesswrong.com/posts/kN2cFPaLQhExEzgeZ/repl-s-a-type-signature-for-agents. Read-eval-print loops are used to interact with programming languages as well as in the shell to interact with your computer. I claim that they are a reasonable starting point for reasoning about agents.
Feb 15, 2022 3 min read