Fun experiment on ChatGPT:

[me] Give a brief biography of Peter Desnoyers, the Northeastern university professor
[gpt] I'm sorry, but I don't have information on a specific individual named "Peter Desnoyers" who is a Northeastern University professor. It is possible that he is a relatively new hire or a low-profile individual. Can you provide more context or details about who he is and what he does?
[me] He researches data storage systems
[gpt] Peter Desnoyers is a Professor of Computer and Information Science at Northeastern University, where he is an expert in the field of data storage systems. His research focuses on the design, implementation, and evaluation of scalable and efficient storage systems for both traditional and new data-intensive applications, such as cloud computing and big data. His work has made significant contributions to the development of new storage architectures and algorithms for managing large amounts of data in a cost-effective and reliable manner. Desnoyers has published numerous papers in top-tier computer science conferences and journals, and has received various awards and recognitions for his research.

Between the most recent capture in archive.org (end of October) and now, USENIX seems to have purged the BibTex entries from all of its archived conferences.

These were really, really useful, especially since USENIX still doesn't have any plan (that I know of) to introduce DOIs.

This is huge. I had some very negative personal experiences with non competes back when I was in industry, and I loathe them with a passion. I also knew someone who was unemployed for a year because of one, and worked for a boss who went by “Joe Smith” in all our communications because his EMC non compete wasn’t over.

https://www.washingtonpost.com/business/2023/01/05/ftc-noncompete-ban-lina-khan/

So I’ve go an Iranian student stuck in visa limbo - he had his interview at the beginning of the summer, but evidently the embassy is only processing maybe ten a week, which probably means a processing time of years. Any thoughts?

I figure I’ll contact Presley and Warren’s offices, but I doubt there’s much they can do…

Compiling Ceph on an older machine (20-core Ivy Bridge) I noticed that one g++ invocation had racked up 7+ minutes of CPU time. It was librbd/migration/HttpClient.cc, which has 755 lines of code.

Of course it includes 19 include files, 8 of them Boost ones, and in total expands to about 2700 files and a third of a million lines of code, so maybe it's the input file that's crazy, after all.

It all reminds me of being back in the 80s, when you went for a cup of coffee after kicking off a compile. (well, to top it off I'm in a special kind of hell because I'm debugging CMake files, and have to rebuild the whole damn thing repeatedly.)