Extreme heat wave in Siberia
Crazy temperatures day and night
38.1C Zabelovka lat 52
36.7C Kurgan lat. 55
36.4C Isim lat 56
35.7C Majsk lat 57
34.3C Novyj Vasyugan lat. 58 after a tropical night
Even more insane Makusino lat 55N Tmin 23.1C Tmax 35.6C
Next days much worse ! pic.twitter.com/uNo5Rdhstb
— Extreme Temperatures Around The World (@extremetemps) June 2, 2023
Perhaps a reader can help with a more idiomatic translation….
COVID-19 vaccination-related myocarditis: a Korean nationwide study European Heart Journal. N = 44,276,704 (nation-wide study). From the Conclusion: “COVID-19 [Vaccination-Related Myocarditis (VRM)] was confirmed in 480 cases (1.08 cases per 100 000 persons). Although COVID-19 VRM was rare and showed relatively favorable clinical courses, severe VRM was found in 19.8% of all VRM cases. Moreover, [Sudden Cardiac Death (SCD)] should be closely monitored as a potentially fatal complication of COVID-19 vaccination.” Myocarditis = “Inflammation of the heart muscle, usually following a virus.” In generally, I’m skeptical of cross-national studies because of confounders (for example, diet). Nevertheless, certainly chimes with what IM Doc has been saying for some time, if not numerically, at least as an effect.
* * *
Brain fog in long COVID limits function and health status, independently of hospital severity and preexisting conditions (research report) Frontiers in Neurology. N = 530. From the Abstract: “A year after COVID-19 infection, [Brain Fog (BF)] persists in a third of patients. COVID-19 severity is not a predictive risk factor. BF associates with other longCOVID and independently associates with persistent debility.” One third? Do the math….
* * *
A Salesman’s Trick, Ignoring R0, Shaming, Conspiracy, Premature Declaration, Strategic Omission, and Fanciful Fiction Science-Based Medicine. Close reading of a single paragraph by GBDer Richard M. Salsman.
* * * * * *
The dictatorship of the church Africa is a Country
Germany: Police break up banned far-left protest in Leipzig Deutsche Welle
What Are German Fighter Pilots Doing in China? Der Speigel
Dear Old Blighty
The Startup Party: reflections on the last 20 years, what could replace the Tories, and why Dominic Cummings Substack. I confess to a sneaking esteem for Cummings (he’s certainly smarter and more focused than Bannon). “Insiders are sure to panic further and accelerate the forces they dread.” Worth a read.
UK government refuses to hand over WhatsApp messages to COVID inquiry International Business Times
New Not-So-Cold War
Ukraine’s Zelensky: We Are Ready for Counteroffensive (interview) WSJ
The Ukrainian Military Is In Bad Shape Moon of Alabama
* * * * * *
Ukraine in last-ditch appeal for EU to end grain import curbs Politico (Brunches with Cats). Brunches with Cats: “IMO, this article isn’t clear enough upfront that the ‘EU ban’ applies to only five countries. However, it goes into the politics in more depth than I’ve seen elsewhere, particularly regarding Poland.”
Biden celebrates a ‘crisis averted’ in Oval Office address on bipartisan debt ceiling deal AP [yawns]. What? Did you say something?
Debt deal imposes new work requirements for food aid and that frustrates many Democrats Boston Globe. They may be “frustrated,” but you know what? They’ll keep “fighting.” So it’s all good.
Crypto collapse? Get in loser, we’re pivoting to AI Attack of the 50 Foot Blockchain Attack of the 50 Foot Blockchain. A must-read:
Anil Dash observes (over on Bluesky, where we can’t link it yet) that venture capital’s playbook for AI is the same one it tried with crypto and Web3 and first used for Uber and Airbnb: break the laws as hard as possible, then build new laws around their exploitation.
The Writer’s Guild of America, a labor union representing writers for TV and film in the US, is on strike for better pay and conditions. One of the reasons is that studio executives are using the threat of AI against them. Writers think the plan is to get a chatbot to generate a low-quality script, which the writers are then paid less in worse conditions to fix. [Guardian]
Executives at the National Eating Disorders Association replaced hotline workers with a chatbot four days after the workers unionized. “This is about union busting, plain and simple,” said one helpline associate. The bot then gave wrong and damaging advice to users of the service: “Every single thing Tessa suggested were things that led to the development of my eating disorder.” The service has backtracked on using the chatbot. [Vice; Labor Notes; Vice; Daily Dot]
Digital blackface: instead of actually hiring black models, Levi’s thought it would be a great idea to take white models and alter the images to look like black people. Levi’s claimed it would increase diversity if they faked the diversity. One agency tried using AI to synthesize a suitably stereotypical “Black voice” instead of hiring an actual black voice actor. [Business Insider, archive]
* * *
I suppose we could say the same for most of our systems and institutions just now. They work great, “once the propensity to hallucinate is ironed out.” Perhaps AI is, at it were, “holding a mirror up to nurture.”
Evaluating ChatGPT4 in Canadian Otolaryngology-Head and Neck Surgery Board Examination using the CVSA Model (preprint) medRxiv. From the Abstract: “ChatGPT-4 achieved a passing score in the sample exam, and demonstrated the potential to pass the Canadian Otolaryngology-Head and Neck Surgery Royal College board examination. . Further adjustments are necessary to yield safer and more accurate answers for clinical implementation.” “Hallucinations” anthropomorphizes, so I’m not sure I’m comfortable with that framing.
* * *
Security News This Week: AI Is Being Used to ‘Turbocharge’ Scams Wired. This is what happens when AI goes mainstream, because in our financialized economy, scams are the mainstream. Not “Uncanny Valley,” but “Hallucinatory Valley.” It’s hard for me to imagine that all the brain geniuses in SIlicon Valley — all the Founders shocked, shocked because nobody expects the AI inquisition — didn’t see it coming.
Google’s New AI-Powered Search Is A Beautiful Plagiarism Machine Forbes. Google is just hoovering up big chunks of text from online sources, and if it’s more accurate than ChatGPT, that’s why. And the sources don’t get a link, either, so there are no clickthroughs. “Once the rockets are up, who cares where zey come down….”
Undetectable Watermarks for Language Models Cryptology ePrint Archive. “Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in model outputs, by altering the output distribution. We ask: Is it possible to introduce a watermark without incurring change to the output distribution?” Why?
* * *
‘Much easier to say no’: Irish town unites in smartphone ban for young children Guardian (Re Silc).
New way to place your bets on boom and bust of shipping cycle Freight Waves. Reads like a product placement, but still interesting.
Big Brother Is Watching You Watch
The Twilight of Freedom Craig Murray
Realignment and Legitimacy
Conservative Americans are building a parallel economy The Economist
How a Staunchly Blue State Let MAGA Seep In Politico. “Seep”?
Imperial Collapse Watch
The Man Who Knows What the World’s Richest People Want (and How To Get It) Vice. Structurally (sociolologically) this is extremely interesting. How many other people are “two degrees of separation from any significant gatekeeper in the world,” and what do they do?
Zeitgeist 2023 Heisenberg Report. Implications of Dollar General’s weak report. Worth a read!
Idle rich baffled by poor people’s distaste for dangerous, low-paying jobs Boing Boing (Re Silc).
The grid part II – the golden age of the power industry Construction Physics. Part I.
An Anthropologist of Filth Harpers. Chuck Berry
Antidote du Jour (via):
— Mark Smith Photography (@marktakesphoto) June 3, 2023
See yesterday’s Links and Antidote du Jour here.