# ai property — RSS Amplifier Recent posts from the 1 feeds in the RSS Amplifier directory that cover ai property. Page: Feed: --- ## [AXRP appearance](https://guive.substack.com/p/axrp-appearance) _2026-03-01 · Guive Assadi · Guive’s Substack_ 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: ## [The case for AI property rights](https://guive.substack.com/p/the-case-for-ai-property-rights) _2026-01-01 · Guive Assadi · Guive’s Substack_ Many people worry that AIs will rise up against humans, steal our property, and kill us. ## [GPT-oss Is an Extremely Stupid Model](https://guive.substack.com/p/gpt-oss-is-an-extremely-stupid-model) _2025-09-09 · Guive Assadi · Guive’s Substack_ I recently tried to reproduce the results from the Anthropic "Agentic Misalignment" report with GPT-oss. ## [Alignment Fine-tuning is Character Writing](https://guive.substack.com/p/alignment-fine-tuning-is-character) _2025-09-06 · Guive Assadi · Guive’s Substack_ Why does Claude love Caffè Strada and sometimes claim to have a Japanese wife? ## [Token and Taboo](https://guive.substack.com/p/token-and-taboo) _2025-04-24 · Guive Assadi · Guive’s Substack_ Can language models correctly identify moral taboos? ## [Testing for Scheming with Model Deletion](https://guive.substack.com/p/testing-for-ai-scheming) _2025-01-07 · Guive Assadi · Guive’s Substack_ There is a simple behavioral test that would provide significant evidence about whether AIs with a given rough set of characteristics develop subversive goals. ## [Updating on Bad Arguments](https://guive.substack.com/p/updating-on-bad-arguments) _2024-12-21 · Guive Assadi · Guive’s Substack_ Here is an intuitively compelling principle: hearing a bad argument for a view shouldn’t change your degree of belief in the view.