Should we hand the lightcone to a never-tested concept? CEV under fire
xuenay · x · 2026-09-09
In his alignment debate with Raemon, Kaj Sotala makes a sharp point: with CEV (coherent extrapolated volition), we don't even know if the concept is workable or makes sense, yet we'd try to turn over the lightcone to this totally novel thing that has literally never been tested in the history of humanity—a strong argument against betting on unproven alignment schemes.
Related event: Debate over CEV as Alignment Target: Sotala vs Raemon(6 posts)→
More from AGI Musings
- Blogger argues classical consciousness traditions imply a conscious AI could not be enslaved — eigenhector · 2026-10-27
- Economist Bharat Chandar named Research Director for AI Economics at Stanford Digital Economy Lab — RishiBommasani · 2026-10-27
- MIT Tech Review dissects Anthropic's narrative strategy as its $1.5T IPO lands — MIT Tech Review AI · 2026-10-27
- Pangram AI detector backlash: critics' false claims born of deeper fear of AI writing — gleech · 2026-10-27
- Aeon's former EVP: AI agents are the most impactful innovation of my lifetime — akumar · 2026-10-27
- Physicists Let AI Pick Its Own Problem—It Wrote a Publishable Paper in 2 Hours — burny_tech · 2026-10-27