An update from us here at PBS π
07.08.2025 18:27 β π 3484 π 2002 π¬ 51 π 128@gcs-hpc.bsky.social
Trilingual HPC expert and benchmarker, erstwhile educator and occasional translator. Princeton Ph.D. (EECS).
An update from us here at PBS π
07.08.2025 18:27 β π 3484 π 2002 π¬ 51 π 128Motorola 68000. π
09.08.2025 03:07 β π 1 π 0 π¬ 1 π 0Motherfucking wind farmsβ¦
30.07.2025 17:02 β π 46090 π 17388 π¬ 1150 π 2308"A full 16 percent (that's over one in six people)". Actually, 16% is under one in six (1/6=0.16+0.02/3).
22.07.2025 23:14 β π 0 π 0 π¬ 1 π 0history | grep "cmd_you_want_to_repeat" | tail
usually works for me with no ill effects.
Perhaps it's something up with which he will not put. (Stolen from someone famous whose name I can't remember.)
03.07.2025 22:06 β π 0 π 0 π¬ 0 π 0I wouldn't.
retractionwatch.com/2025/06/30/s...
5-panel comic. (1) [teacher with long hair next to whiteboard] TEACHER: Iβm supposed to give you the tools to do good science. (2) [teacher addressing students] But what *are* those tools? Methodology is hard and there are so many ways to get incorrect results. What is the magic ingredient that makes for good science? (3) TEACHER: To figure it out, I ran a regression with all the factors people say are important: [embedded list in sub-panel, cut off at end] Outcome variable: correct scientific results. Predictors: collaboration; skepticism of othersβ claims; questioning your own beliefs; trying to falsify hypotheses; checking citations; statistical rigor; blinded analysis; financial disclosure; open data (4) TEACHER: The regression says two ingredients are the most crucial: 1) genuine curiosity about the answer to a question, and 2) ammonium hydroxide. (5) STUDENT: Wait, why did *ammonia* score so high? How did it even get on the list? LONG HAIR: ...And now youβre doing good science!
Good Science
xkcd.com/3101/
Β‘Hasta luego y gracias!
11.06.2025 17:21 β π 1 π 0 π¬ 0 π 0As of this month we're closer to 2050 than we are 2000.
Have a great day!
More BS (and I don't mean BlueSky) from "AI slop".
Cc: @chromamagic.com
I've never attended ISC, and it is unlikely I will ever attend unless I get rich enough to afford it on my own dime.
30.04.2025 00:18 β π 2 π 0 π¬ 0 π 0Funny you should mention "AI slop": www.theguardian.com/commentisfre...
30.04.2025 00:15 β π 2 π 0 π¬ 1 π 0Tariffs xkcd.com/3073
08.04.2025 00:03 β π 31661 π 8874 π¬ 264 π 477Join us 26-MAR-2025 1700 UTC at aka.ms/hpc_hallway to mark 5 years of #HPChuddle #HPChallway - the weekly open informal online gathering of #HPC people set up to support our HPC community as in-person meetings closed down & later inspiring creation of @hpc.social
hpc-hallway.github.io/The-Hallway/
The thing is, gallium arsenide will never come even close to being as cheap as silicon.
Don't get me wrong. I like GaAs. I got my Ph.D. by bouncing low-energy electrons off of the (110) surface of pure GaAs single crystals. π
2/2
GaAs has been the semiconductor of the future for decades, presumably because of its higher electron mobility. Unfortunately, Seymour Cray's CRAY-3, based on GaAs, was no faster than the ho-hum silicon CRAY C90 when they both became almost simultaneously available in the mid 90s.
1/2
The directive-based predecessors to #OpenMP that were available in both Cray Research, Inc., and Silicon Graphics, Inc., compilers in the early to mid-90s. After the so-called merger, OpenMP arose from both.
06.03.2025 02:12 β π 0 π 0 π¬ 0 π 0Stand with UKRAINE! #standWithUkraine
28.02.2025 21:16 β π 100 π 29 π¬ 4 π 0Cameo by The Addams Family's Thing? π€ππ
17.02.2025 18:54 β π 1 π 0 π¬ 0 π 0Never let go of your self-esteem, James!
17.02.2025 18:51 β π 2 π 0 π¬ 1 π 0Breaking from JCC: GROMACS reaches a new height in #HPC scalability! @mpibp.bsky.social @mpi-nat.bsky.social onlinelibrary.wiley.com/doi/full/10....
15.02.2025 16:14 β π 3 π 3 π¬ 0 π 0Huh. (1+i)Β² = 2i. How is that real? On the other hand, you can count on zz* to be the real thing!
16.02.2025 21:44 β π 2 π 0 π¬ 0 π 0Is it just me or is this something that should have remained in the "proofs of concept that didn't need proving" category? π€
16.02.2025 21:36 β π 1 π 0 π¬ 0 π 0I wrote a little text to accompany this slide. It sums up the hour-long presentation in just a few words.
www.glennklockwood.com/garden/diffe...
#HPC #AI
I suppose it sorta makes sense that early humans traded off fur coats and physical strength for big brains that allowed us to create clothes and tools and now weβre apparently trading off those big brains for the ability to use hallucinatory auto-complete to write reports for us.
10.02.2025 16:23 β π 1083 π 228 π¬ 34 π 11Meme showing a kid making a gesture of disbelief, and the legend "When you ask someone a boolean question and they return a string".
Lots of people, a lot of the time.
[Found on #Mastodon.]
@cisnerosres.bsky.social π
21.01.2025 14:33 β π 3 π 1 π¬ 0 π 0You missed the fourth spirit.
Tequila.
Wasn't that something the recently elected convicted felon suggested last time he was occupying the White House? π€ (Let's nuke hurricanes! Yes, he suggested that in 2019.)
21.12.2024 18:48 β π 0 π 0 π¬ 0 π 0