About me:
— Aaron Michael Turner
— UK citizen, US national
— Born 24 June 1961 in the UK
— Moved to the US as an infant, brought up in New York City, resident in the UK since 1969
— BSc (2.1) in Computer Science from Queen Mary College, University of London, 1983
— Joined Sinclair Research Ltd in Cambridge (UK) as a software engineer, 1983
— Founding member of SRL’s "Fifth Generation" AI project at the MetaLab research centre, 1984
— AGI (Artificial General Intelligence) researcher since 1985
— Co-founded AI startup Man-Made Minions Ltd (with SRL colleague Aubrey de Grey) in 1986
— Awarded a bursary for the PRG’s MSc in Computation course at Oxford University, 1995-96
— Looked after my mum 24/7 for 6 years when she had dementia, 2009-15
— Reconstituted MMM as non-profit AGI lab BigMother.AI CIC in 2018
— Founded ML startup Superintelligence Ltd in 2020
— Published a proposed solution to the Outer AGI Superalignment Problem in 2025
I believe very strongly that the nature of the very first superintelligent (or near-superintelligent) AGI that we create will determine the subsequent fate of all mankind for all eternity. Accordingly, I have dedicated most of my life to the pursuit of safe and benevolent AGI. As an independent researcher, I operate outside of the AI mainstream, and am unconstrained by conventional wisdom.
Hi mishka, thanks for commenting. TBH LLM-based chatbots don't really understand either their input prompts or their output continuations, so any LLM-based summary is not going to be particularly reliable. Subsequent to your comment, I have added a TL;DR section, borrowed from the paper's introduction - I hope this helps at least a little. Other than that, I'm afraid there's no real substitute for actually reading the paper in full - I hope you choose to do so!