Engineering Ideas | Roman Leventov | Substack

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…

Jun 1

New

Top

Community

An LLM-based “exemplary actor”

Into and summary This post is the second section of "Aligning an H-JEPA agent via training on the outputs of an LLM-based "exemplary actor", posted…

May 29

Annotated reply to Bengio's "AI Scientists: Safe and Useful AI?"

The AI safety proposal “AI Scientists: Safe and Useful AI?” was published by Yoshua Bengio on May 7, 2023. Below I quote the salient sections of the…

May 8

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…

Apr 24

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…

Apr 18

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…

Apr 8

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…

Mar 20

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…

Mar 10

Engineering Ideas

Engineering Ideas

Ethics, AI Safety, physics of intelligence and agency, organisation and community engineering, methodology.

Recommendations

After Babel Jon Haidt

Mental Contractions

Mental Contractions Pawel Pachniewski

Musings on the Alignment Problem Jan Leike

Sparks in the Wind François Chollet

Rational in the Fullness of Time Alexandr Wang

Engineering Ideas

About Archive Recommendations Sitemap

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts