Engineering Ideas

Home
Notes
Archive
About
New
Top
Discussion
June 2023
Aligning an H-JEPA agent via training on the outputs of an LLM-based "exemplary actor"
This post includes the overview and the conclusion of the article that was posted on LessWrong. Overview In section 2, I describe the “exemplary actor…
May 2023
April 2023
For alignment, we should simultaneously use multiple theories of cognition and value
This post is a follow-up to "A multi-disciplinary view on AI safety research". I elaborate on some arguments behind this view. Computationally tractable…
Scientism vs. people
This post is originally published on LessWrong. The Benefactor, the ancestor of Orwell's Big Brother, is the absolute ruler of OneState. ... He rules…
Goal alignment without alignment on epistemology, ethics, and science is futile
I start to suspect that the concepts of "goals" or "pursuits", and, therefore, "goal alignment" or "goal (mis)generalisation" are not very important. In…
March 2023
Will people be motivated to learn difficult disciplines and skills without economic incentive?
In a recent interview with ABC news, Sam Altman emphasised multiple times that he sees individual AI tutoring as one of the greatest applications of AI…
Comments on Anthropic's AI safety strategy
Anthropic has published its AI Safety strategy: “Core Views on AI Safety: When, Why, What, and How”. High-level thoughts Overall, I like the posted…
Joscha Bach on Synthetic Intelligence [lightly annotated]
Annotated excerpts from a recent conversation between Jim Rutt and Joscha Bach. Link to transcript. The conversation is very dense and there are a lot…
February 2023
Morphological intelligence, superhuman empathy, and ethical arbitration
Morphological intelligence (Levin, 2022) is the ability to solve problems in the morphological space, e.g., navigate to a target morphology of the…
A multi-disciplinary view on AI safety research
This post has been originally published on LessWrong. I didn’t copy the footnotes into Substack because there are too many of them. Please proceed to…
© 2023 Roman Leventov
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing