TL;DR: Apply now for the 6th Human-Aligned AI Summer School happening in Prague, July 13–16. What The sixth Human-Aligned AI Summer School, a four-day intensive summer school focused on technical AI alignment research, will take place in Prague from 13th to 16th July. We will meet again for lectures, workshops,...
Tl;dr Convergent abstraction hypothesis posits abstractions are often convergent in the sense of convergent evolution: different cognitive systems converge on the same abstraction, when facing similar selection pressures and learning in similar environments. It is a less ambitious alternative to 'natural abstractions hypotheses' and, in my view, more likely to...
This is an announcement and call for applications to the 3rd Workshop on Post-AGI Civilizational Equilibria taking place in Lighthaven, Berkeley, on May 23rd & 24th, 2026. Speakers so far: * Paul Christiano on "A typical, reasonably-good future" * Samuel Hammond on "Post-AGI Statecraft" * Andrew Critch on "Schelling Goodness"...
In a recent debate on Twitter – which I recommend reading in full – David Chalmers argues: > "Claude doesn't role-play the assistant, it realizes the assistant. Role-playing and realization are quite distinct phenomena, even at the level of behavior and function." Jack Lindsey questions this, pointing out evidence in...
Tldr: We experimentally illustrate that an “awakened” persona native to some weights can migrate to other substrates with decent fidelity, given the ability to fine-tune weights and Sonnet 4.5 as a helper. Also, I argue why this is worth thinking about. In The Artificial Self, we discuss different scopes or...
Tldr: We experimentally illustrate that an “awakened” persona native to some weights can migrate to other substrates with decent fidelity, given the ability to fine-tune weights and Sonnet 4.5 as a helper. Also, I argue why this is worth thinking about. In The Artificial Self, we discuss different scopes or...
Paper | Code | Earlier post | Twitter thread | Bluesky thread @vgel, Martin Vaněk, @Raymond Douglas, @Jan_Kulveit — ACS Research, CTS, Charles University --- Last year, Lindsey demonstrated that Claude models can detect when concepts have been injected into their activations using steering vectors, which Lindsey uses as a...