Engineering Ideas
Subscribe
Sign in
Home
Notes
Archive
About
New
Top
Discussion
AI romantic partners will harm society if they go unregulated
Recently, when people refer to “immediate societal harms and dangers” of AI, in media or political rhetoric, they predominantly choose to mention…
Aug 1
1
Share this post
AI romantic partners will harm society if they go unregulated
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
1
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…
Jun 1
Share this post
Aligning an H-JEPA agent via training on the outputs of an LLM-based "exemplary actor"
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
May 2023
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
Share this post
An LLM-based “exemplary actor”
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
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
Share this post
Annotated reply to Bengio's "AI Scientists: Safe and Useful AI?"
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
1
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…
Apr 24
Share this post
For alignment, we should simultaneously use multiple theories of cognition and value
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
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
1
Share this post
Scientism vs. people
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
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
1
Share this post
Goal alignment without alignment on epistemology, ethics, and science is futile
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
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…
Mar 20
2
Share this post
Will people be motivated to learn difficult disciplines and skills without economic incentive?
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
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
Share this post
Comments on Anthropic's AI safety strategy
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
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…
Mar 2
Share this post
Joscha Bach on Synthetic Intelligence [lightly annotated]
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
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…
Feb 13
Share this post
Morphological intelligence, superhuman empathy, and ethical arbitration
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
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…
Feb 9
Share this post
A multi-disciplinary view on AI safety research
engineeringideas.substack.com
Copy link
Facebook
Email
Notes
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts