Maxim Raginsky
LightNews LightNews
banner
mraginsky.bsky.social
Maxim Raginsky
@mraginsky.bsky.social
6.6K followers 960 following 2.5K posts
web: http://maxim.ece.illinois.edu
substack: https://realizable.substack.com
Posts Replies Media Videos
mraginsky.bsky.social
November 8, 2025 at 1:40 AM
mraginsky.bsky.social
November 7, 2025 at 5:01 PM
mraginsky.bsky.social
November 2, 2025 at 3:31 PM
mraginsky.bsky.social
afternoon, y’all
November 1, 2025 at 5:50 PM
mraginsky.bsky.social
From my twitter archive:
October 25, 2025 at 5:12 PM
mraginsky.bsky.social
Everyone should read this book by Dijkstra:
Cover of Edsger W. Dijkstra's "A Discipline of Programming".
October 20, 2025 at 9:20 PM
mraginsky.bsky.social
got my Halloween reading all lined up for this year
October 20, 2025 at 3:44 AM
mraginsky.bsky.social
October 19, 2025 at 4:42 PM
mraginsky.bsky.social
evening, all
October 15, 2025 at 12:44 AM
mraginsky.bsky.social
October 12, 2025 at 5:19 PM
mraginsky.bsky.social
closing of the spritz season
October 11, 2025 at 9:16 PM
mraginsky.bsky.social
October 11, 2025 at 2:31 PM
mraginsky.bsky.social
October 10, 2025 at 2:09 AM
mraginsky.bsky.social
🔥
October 5, 2025 at 3:18 AM
mraginsky.bsky.social
Your periodic reminder that Mirowski’s _Machine Dreams_ is a phenomenal book:
October 5, 2025 at 3:16 AM
mraginsky.bsky.social
More gems from the same paper:
13) Why should intelligence be describable by a single number when, in the physical world, describing the behavior of even the lowly electron is often thought to require an infinite dimensional space? 14) In his passionate and persuasive attack on the politics of intelligence testing, Gould [10, p. 238] seems to console himself with the belief that "Factor analysis •• 0 is, to put it bluntly, a bitch ••• though its mathematical basis is unassailable." Personally I am more comfortable with the conclusion that many results from intelligence testing can be safely rejected, not by impugning that the authors' subconscious political beliefs have corrupted their data but, more simply, by demonstrating their incompetence in model building.
October 3, 2025 at 12:55 AM
mraginsky.bsky.social
what a difference 10 years make
October 2, 2025 at 10:19 PM
mraginsky.bsky.social
there it is!
September 30, 2025 at 4:00 PM
mraginsky.bsky.social
Rudolf Kalman put it nicely (and provocatively): link.springer.com/chapter/10.1...
Quote from R. Kalman, "Identification from real data": For an objective outsider, much of the historical development of statistics is a long series of attempts to dodge the inevitable implications of uncertainty. Whenever the conventional statistical treatment of a problem gives a unique (certain) answer, as in maximum likelihood estimation, in least squares, ... , common sense should tell us that such a miracle is possible only if additional assumptions (deus ex machina) are imposed on the data which somehow succeed in neutralizing the intrinsic uncertainty. We shall use the technical term "prejudice" for such assumptions. In other words, statistical methodology has been handicapped because statisticians have become mesmerized by the deep-seated hope of giving certain answers to problems where the uncertainty is intrinsic. This is politics, not science. For example, least squares is very popular because it always gives a unique answer. But this is exactly where its fatal weakness lies; when we pose Nature a question, as in identification problems, we must not phrase that question in such terms that the answer is predetermined regardless of the nature of the data.
September 27, 2025 at 5:42 PM
mraginsky.bsky.social
lol, lmao
September 26, 2025 at 7:52 PM
mraginsky.bsky.social
@supermeyn.bsky.social is a skilled cocktail photographer
September 23, 2025 at 12:57 AM
mraginsky.bsky.social
September 19, 2025 at 3:47 AM
mraginsky.bsky.social
September 19, 2025 at 3:32 AM
mraginsky.bsky.social
I found a clinic for ailing AIs
September 14, 2025 at 4:54 PM
mraginsky.bsky.social
Perfect illustration of the dangers of psychologism. Frege must be spinning in his grave. realizable.substack.com/p/supertzar-...
September 12, 2025 at 3:31 PM