Wow. Another HPC acceleration by AI paper. This is the way
Posts by Doug Eadline
And ... It is not beyond the realm of possibility that we may see AI companies pivoting to shoes in the future
Take a chip that runs hot and has a 10% annual failure rate, put it in a more critical environment with cosmic rays
:double facepalm
yea but we are headed "toward true cognitive abundance" what ever that is
Let me see if I got this, "We trained our AI on all your text and code, so your job is not needed, bye. We'll continue to scrape the new AI generated interwebs for even more content because we put the original creators out of work. Profit!" Did anyone read the papers about about model collapse?
Darn, there goes my business idea,
"Dummy Servers Inc (R)"
"We are cheaper than the real ones that it you will never turn on"
First week of June, east coast
AI for science!
Registration is OPEN for #TPC26!
Join us for one of the most forward-thinking conferences in tech, policy, and leadership. Where brilliant minds come together to shape the future.
Early-bird pricing here: ow.ly/azv950Ymum0
#artificialintelligence
And when the bubble pops
We all hope the price drops
What? All I can say at this point "Looks like you picked the wrong week to stop sniffing glue"
Yep
Ed, as always nice work. I think the ability of nvidia to keep the generational improvements is going to get harder and the cadence will slow, and GPUs will still have a ~10% annual failure rate, or greater, due to physics as things get smaller, no free next-gen lunch, it is going to cost more
At this point in the game, has anyone noticed that effective use of GenAI requires actual wet intelligence. Just say'n
Agree, a good overview of where we are in all this "AI" hype. IMO his best line "Good stuff here, being distorted by the crazy"
the limitations of the current GenAI tech, we are not there yet and scaling $ and GPUs does not seem to be the way forward.
What intrigues me is if there is a correction/implosion in GenAI, there will be a large collection of hardware that can be repurposed for HPC (for building data models) /end
Thanks. I have thought about some of theses issues as well. I also wonder about how the GenAI market, which has not yet shown it can make money, can drive HPC in the long term. There are/will be wins for sure but enough to justify the level of investment is questionable based on /1
Nice work
Find it here earth.nullschool.net#current/wind...
Thanks to GFS / NCEP / US National Weather Service
Bit windy today on the east coast
Sorry son, I have to report you. We just cant have this reckless hooliganism on the interwebs.
Please share to help spread the word!
We have already have some applications for the #HPC system administrator open position in our team at Ghent University (Belgium), but it's not too late yet!
Deadline to apply is Sun 1 Feb 2026.
jobs.ugent.be/job/Ghent-Sy...
Show floor safari from sc25 (BTW, this is obviously AI generated because, I would never ask such goofy questions and try and explain QC)
ow.ly/mhHC50Y0F1m
Wait, what? You are joking right?
We need a safe word to know it is you.
I call it the universal assembly language.
Score! Disk included
Yes but does it do lightscribe ?
Fair point. Although they both wrote script, which differed from the book (Saturn vs Jupiter). Also, the book was released after the film. So instead of a full point off, maybe just a half point
Thanks, I found myself explaining AI to my friends and family. Was getting repetitious, so I started writing a short piece to help explain things in non-tecnical terms, well then it got long ... now they said it is too long, oh the tortured irony I create