The Great Debate @ARITH23: John Gustafson and William Kahan on HackerTube: recommended by 1 Hacker News commenter across 1 month, 2017–2023.
talk · advanced · evergreen
A 95-minute recorded debate at the ARITH23 computer arithmetic conference between John Gustafson, proponent of unums/posits, and William Kahan, architect of IEEE 754 floating point. They argue the merits of the new number formats versus conventional floats and interval arithmetic.
It is the go-to primary source whenever HN discusses posits versus IEEE floats, valued for Kahan's sharp critique despite the poor audio.
“Audio quality is not great but there are links to slides from Gustafson and Kahan”
4 Hacker News comments link this video. Each one links back to its thread.
The Great Debate @ARITH23: John Gustafson and William Kahan ▶ this video Audio quality is not great but there are links to slides from Gustafson and Kahan
in “Beyond Floating Point: Next-Generation Computer Arithmetic [pdf]” · View on HN
A related discussion about number types: The Great Debate @ARITH23: John Gustafson and William Kahan ▶ this video Kahan points out disadvantages of interval maths.
in “Aztec monks with 1/55 HP no longer die when picking up or dropping a relic” · View on HN
Original posits are variable width, making them nearly useless for high performance parallel computations. Later versions don't add anything of use for low precision neural networks, and lack of hardware support anywhere make them too slow for anything other than toying around. See also [link] and ▶ this video
in “Will Floating Point 8 Solve AI/ML Overhead?” · View on HN
I did some reading on unum a while back, inc. Kahan's criticisms. There's another side. There's a vid on youtube with Kahan and Gustafson talking over it. Kahan goes in like a wolf onto a lamb, much to gustafson's shock and hurt. Gustafson points out some of Kahan's criticisms are plain wrong, even citing the page in the book, then says something like "we should be working together on this, why aren't we working together?" Kahan doesn't respond. Kahan may be right or wrong but his attitude is weirdly hostile, and Gustafson is no n00b about floats. Edit: I think this is it (but it's been a while) ▶ this video
in “Posits, a New Kind of Number, Improves the Math of AI” · View on HN