SociaLLM: proposal for a language model design for personalised apps, social science, and AI safety research

I first proposed this model here, as a base model for a proposed app to improve global online discourse through personalised comment ordering on…

Roman Leventov

Dec 6, 2023

Proposal for improving the global online discourse through personalised comment ordering on all websites

This is a description of a project I’ve been thinking about making in the last few weeks. I’m looking for feedback and collaborators. [BetterDiscourse]…

Roman Leventov

Jun 1, 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

Roman Leventov

May 29, 2023

An LLM-based “exemplary actor”

Design and properties of a simple language model cognitive architecture

Into and summary

This post is the second section of “Aligning an H-JEPA agent via training on the outputs…

Roman Leventov

Apr 24, 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…

Roman Leventov

Feb 13, 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 species. For example, tadpoles with scrambled craniofacial…

Roman Leventov

Feb 8, 2023

A multi-disciplinary view on AI safety research

Roman Leventov

Jan 20, 2023

Critique of some recent philosophy of LLMs’ minds

Roman Leventov

Jan 14, 2023

How evolutionary lineages of LLMs can plan their own future and act on these plans

TL;DR

LLM lineages can plan their future and act on these plans, using the internet as the storage of event memory. “We” are not guaranteed to “out-OODA” them…

Roman Leventov

Jan 7, 2023

AI psychology should ground the theories of AI consciousness and inform human-AI ethical interaction design

This post is a follow-up to Buck’s “The case for becoming a black-box investigator of language models”. Here, I want to highlight two further…

1 response

About Engineering IdeasLatest StoriesArchiveAbout MediumTermsPrivacyTeams