Founding Engineer (appeared anonymously)
A founding engineer at Abliteration AI, the lab behind abliterated-model-large-v2, a version of Z.ai's GLM-5.3 with refusals removed for offensive cybersecurity research. Appeared on ThursdAI without giving a name, to explain how abliteration works, why the lab released a fully uncensored model, and how they think about the safety debate around it.
Abliteration AI founding engineer appeared as a guest on ThursdAI, the weekly AI news podcast hosted by Alex Volkov. Browse the full guest directory or subscribe on Substack to never miss an episode.
ThursdAI — The weekly AI podcast. Every Thursday, live.
Subscribe Free →