My personal Substack
Live Last read · last published · next check
Recently, I appeared on Daniel Filan’s AXRP podcast to discuss my article arguing for AI property rights. I’m happy with how the podcast turned out; I honestly think it’s a bit more interesting than the article. You can listen to the episode here:
Many people worry that AIs will rise up against humans, steal our property, and kill us.
I recently tried to reproduce the results from the Anthropic "Agentic Misalignment" report with GPT-oss.
Why does Claude love Caffè Strada and sometimes claim to have a Japanese wife?
Can language models correctly identify moral taboos?
There is a simple behavioral test that would provide significant evidence about whether AIs with a given rough set of characteristics develop subversive goals.
Here is an intuitively compelling principle: hearing a bad argument for a view shouldn’t change your degree of belief in the view.
This is Guive’s Substack.
