Victor Muraviev

Victor Muraviev (0xVM7) is an AI safety and alignment researcher, working as a key member of aligning.si. For approximately a decade, he has worked on AGI and ASI alignment.

You can see his writings on AI alignment, development, philosophy, ontology and epistemology, including various architectures, including but not limited to LLMs, harnesses and more, on his X profile: 0xVM7, as well as on his website.

The majority of his work is currently private.

Contact

Personal: me@victorm.co.uk

Aligning SI, with "0xVM7" in the subject line: comms@aligning.si