Summary
For a recent talk at the MAISI-Iliad Safety Orientation, I put together some introductory slides on Solomonoff induction and AIXI . I think these slides are a very good modern introduction to the topic, specifically designed to address many common misconceptions which I tend to encounter (including or especially on LW). In this version of the slides, I highlight some work on AI safety applications by Michael Cohen and others. Also, this is an "opinionated" introduction, with a definite slant towards things AIXI Labs is working on. I used heavy AI assistance to produce the slides, particularly graphics. But I also used effort very highly. The content is mostly AI use level 1 in Jacob Hilton's system . Thanks also to Elena Kayayan for substantial improvements to legibility and quality. Discuss
Original text(via LessWrong)
For a recent talk at the MAISI-Iliad Safety Orientation, I put together some introductory slides on Solomonoff induction and AIXI.
I think these slides are a very good modern introduction to the topic, specifically designed to address many common misconceptions which I tend to encounter (including or especially on LW). In this version of the slides, I highlight some work on AI safety applications by Michael Cohen and others. Also, this is an "opinionated" introduction, with a definite slant towards things AIXI Labs is working on.
I used heavy AI assistance to produce the slides, particularly graphics. But I also used effort very highly. The content is mostly AI use level 1 in Jacob Hilton's system.
Thanks also to Elena Kayayan for substantial improvements to legibility and quality.
Only about 795 characters could be extracted — the rest did not come through (common on sites that need scrolling or a login). Read the original for the full piece.
Published by LessWrong
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗