Archive - Joe Carlsmith's Substack

Takes on "Alignment Faking in Large Language Models"

What can we learn from recent empirical demonstrations of scheming in frontier models?

Dec 18, 2024 •

October 2024

Video and transcript of presentation on Otherness and control in the age of AGI

An attempt to distill down the whole "Otherness and control" series into a single talk.

Oct 8, 2024 •

September 2024

Extended audio/transcript from my conversation with Dwarkesh Patel

Extra content on my Otherness series, AI takeover, p(God), and more.

Sep 30, 2024 •

June 2024

Loving a world you don’t trust

Garden, campfire, healing water.

Jun 18, 2024 •

March 2024

January 2024

On the abolition of man

What does it take to avoid tyranny towards the future?

Jan 18, 2024 •

Being nicer than Clippy

Let's be the sort of species that aliens wouldn't fear the way we fear paperclippers.

Jan 16, 2024 •

An even deeper atheism

Who isn't a paperclipper?

Jan 11, 2024 •

Does AI risk “other” the AIs?

Examining Robin Hanson's critique of the AI risk discourse.

Jan 9, 2024 •

When "yang" goes wrong

On the connection between deep atheism and seeking control.

Jan 8, 2024 •

#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