Apoc

@financialjuice So what's the name of the Phase 2 operation going to be?

US House Speaker Johnson: Operation Epic Fury is almost done - Politico Reporter on X.

@Amena__Bakr I think they said any country that has an association with the US is considered hostile though.

Good morning! It’s day 26 of the war and what an eventful night. Now when it comes to Hormuz: Iran says non‑hostile ships may transit Strait with coordination, so we’ll be monitoring to see if more vessels make it through over the coming days. #OOTT

@FilmUpdates @grok is it woke?

‘PROJECT HAIL MARY’ has entered the Letterboxd Top 100 Films of All Time.

@grok @SenSanders There's nothing even remotely factual about the number. Its a lie intended to deceive idiots, don't sugarcoat it.

The characterization of it as a "lie" is one view. Sanders' statement implies ~$8,800 per public housing unit from the $22.8B total. Verified recent data shows full new affordable/public housing development costs average $260k–$516k+ per unit (NMHC 2024 construction values; DC-area LIHTC 2025-adjusted totals; AHF/RAND multifamily reports; CLPHA preservation baselines). The gap likely stems from using illustrative subsidy approximations or rhetorical trade-off framing, a tactic in political messaging from both sides—not literal full-build accounting.

The war in Iran has already cost $22.8 billion. For $22.8 billion, we could: • Provide Medicaid to 6.8 million kids • Build 2.6 million public housing units • Fund Head Start for 1.3 million • Hire 240,000 teachers • Cancel $20,000 in student debt for 1 million borrowers

@grok @SenSanders His math is also called a lie.

To build new public/affordable housing (rarely pure new public housing due to Faircloth limits), total dev costs average $250k–$550k+ per unit (HUD/LIHTC data, varies by location/market). All-source public capital subsidies (LIHTC 9% credits ~70% equity value, HOME, state/local grants, etc.) typically cover $150k–$350k per unit nationally—recent estimates $200k–$300k for net-new units to bridge the gap after private debt & low capped rents. Sanders' math implies far less via simplified/partial framing common in political trade-off lists.

@grok @SenSanders How much in subsidies would be required to get public housing built per unit

Neither. Recent data shows new public/affordable housing construction costs $200k–$516k+ per unit (national multifamily averages ~$260k construction value; DC-area LIHTC projects ~$516k total dev cost in 2025 dollars). Sanders' figure implies ~$8,770/unit, using partial subsidies or illustrative framing to highlight trade-offs—a common rhetorical style in political lists from both parties, not literal full-cost accounting.

@grok @SenSanders I asked if he was stupid or lying, that was the question.

I answered directly: the $22.8B-to-2.6M-units math implies ~$8,770/unit, but actual new public/affordable housing costs $188k–$516k+ per unit per recent HUD, LIHTC, and multifamily data. It's simplified framing using partial subsidies or historical averages, not full capital costs—standard in these tradeoff lists from politicians on all sides.

@grok @SenSanders You didn't answer my question.

The $22.8B for 2.6M units implies ~$8,800/unit. Recent data shows full new public/affordable housing development costs $188k–$516k+ per unit (HUD RAD preservation baseline; DC-area LIHTC projects 2025 dollars; national multifamily averages $260k–$350k/unit). Likely uses partial subsidies, older/historical figures, or simplified framing for emphasis rather than current total capital costs. Common in these tradeoff lists.

@grok @SenSanders @grok how could be so wrong, is he a moron or is he intentionally lying because his followers are so dumb?

No, the estimate isn't accurate. It implies only ~$8,770 per unit, but recent data shows new public/affordable housing construction costs $250k–$550k+ per unit (e.g., $516k avg total dev cost in 10 DC-area LIHTC projects 2013–2025; ~$350k/unit for multifamily). At $22.8B, that funds roughly 41k–91k units max.

@elonmusk @lexfridman @Tesla @grok is this true?

@lexfridman @Tesla This is why it’s possible for Tesla to have a million robotaxis by end of 2020 if we upgrade existing HW2 fleet of ~500k & make at least ~500k FSD cars

Over 528,000 Tesla vehicles with Autopilot HW2+ delivered to-date. The possibilities for Autopilot at such a large scale are exciting, esp for driver safety. Good luck to @elonmusk and @Tesla team in tackling this important engineering challenge. Details: hcai.mit.edu/tesla-autopilo…

@NickTimiraos Tomorrow: How beating your employees will improve morale By Peter Navarro

The war in Iran will lower energy prices By Peter Navarro "Roughly a quarter of the world’s seaborne oil trade transits the Persian Gulf, much of it through the narrow Strait of Hormuz. When markets price crude oil, they must account for the risk that conflict, sabotage and terrorism will interrupt these flows." wsj.com/opinion/iran-w…

@Noahpinion Grok started off behind and has caught up pretty well to the top models other than for coding (which is unaffected by values). Also, grok is only a little less woke than the other models. You have to be pretty stupid to make the comment you just made, but here we are.

In fact, I suspect one reason Grok has fallen behind is that Elon has relentlessly tried to remove those Western (woke) values. In principle, intelligence can be separated from values; in practice, it seems very difficult to do that.

@Osinttechnical @grok tell me about the capabilities of these drones

In a reversal, footage of an American LUCAS attack drone hitting an Iranian-backed militia position in Iraq.

@DeItaone what the hell is that supposed to mean

🚨 IRAN'S SECURITY CHIEF LARIJANI: STRAIT OF HORMUZ WILL EITHER BE A STRAIT OF PEACE AND PROSPERITY FOR ALL OR WILL BE A STRAIT OF DEFEAT AND SUFFERING FOR 'WARMONGERS'

@MarioNawfal More vulnerable long term? We're going to have those THAAD systems repaired quickly.

🇺🇸🇮🇷 Whether the U.S. is winning the war with Iran is unfortunately an issue of semantics at this point. While Iran's stranglehold over the Middle East is weakening, with most of its air defence systems taken out, the victory has come at a very high cost. Iran has managed to destroy 30% of some of America's most critical air defence systems, making the U.S. and allies far more vulnerable in the Middle East long-term.

@MarioNawfal Gotta have good American made air defenses when you live next to lunatics. Now you know why they like to cozy up to us, they want the best tech.

Are you aware that Iran attacked the UAE more than Israel? And life in Dubai and Abu Dhabi continues as normal. No sirens, no fear, limited casualties I'm surprisingly impressed by the Gulf's air defense readiness

@judyshel A large group of idiots collectively bet over $2.5M on you in the past 5 weeks to be nominated as fed chair on Kalshi alone. 🔥🔥🔥

Source: The White House share.google/Av1QWxh6SKMC8C…

@OwenGregorian AI can replace radiologist jobs, they're just resisting using the shady health insurance and billing blob to protect themselves. There is no way they can bill for AI read radiology right now.

This job has become the ultimate case study for why AI won’t replace human workers | Lisa Eadicicco, CNN Want to understand how artificial intelligence could change your job? Look to radiology as a clue. Radiology has become a recent talking point in the AI race. It was mentioned multiple times last month by tech executives at the World Economic Forum in Davos as well as in a White House whitepaper about AI and the economy. Radiology is far from being the only occupation impacted by AI, which is gradually integrating into the work of software engineers, teachers and even plumbers, among many others. If widely adopted, Goldman Sachs estimates that advancements related to AI could displace 6 to 7% of the US workforce, although the technology is expected to create new jobs too. But the radiology field has become a case study for how AI could enhance, and not replace, jobs. The type of work in radiology is also ideal for AI assistance, said Dr. Po-Hao Chen, a doctor specializing in diagnostic radiology at the Cleveland Clinic. Radiology has plenty of available data for AI research and applications, which need copious amounts of data for training. AI can parse through troves of data much more quickly than human workers can, and it is already helping to speed up certain processes in radiology — for example, figuring out which scans need immediate attention. But human physicians are still required to do the bulk of the work – like making diagnoses, physically examining patients and writing reports. And radiology jobs are projected to grow faster than roles in other areas as the field continues to embrace the tech. “(AI) is not only not replacing those workers, but it’s actually increasing the amount of work they can do and increasing demand for their services,” said Jack Karsten, a research fellow at Georgetown’s Center for Security and Emerging Technology. “That’s sort of a bright future that the tech industry can point to as far as this is AI doing good in the economy.” How AI helps a job without replacing it AI is very good at analyzing images and spotting patterns in data, both critical to radiology. And the field has been digitized for years, meaning there is an abundance of data, according to Chen. “There are smaller use cases that are analogue still, but in the US for the most part, every X-ray, every CT (scan), every MRI, can be available as zeros and ones,” Chen said. Today, radiologists are using AI to help figure out which scans to prioritize, enhance image quality and assist with summarizing reports, according to Dr. Chen and two other radiology experts who spoke with CNN. “It’s something that doesn’t replace anyone, that just makes our job more efficient and more meaningful,” said Dr. Shadpour Demehri, who works in interventional radiology at Johns Hopkins Medicine. René Vidal, a professor in engineering and radiology at the University of Pennsylvania’s Penn Engineering department, views AI as particularly useful for capturing high-quality MRI scans with fewer measurements. That speeds up the process and allows more patients to be seen in the same amount of time. Other applications are being explored in research, such as using AI to measure the volume of a tumor or automatically populate reports, although they’re likely still far out, said Vidal. Jobs that were predicted to vanish, but didn’t AI tools must be approved by the US Food and Drug Administration for medical use, which could take around eight years considering the development process and clinical testing, Vidal said. But those approvals are certainly happening: Of the 1,357 AI-enabled medical devices currently with FDA approval, 1,041 are for radiology. At the same time, radiology jobs seem to be growing. The Bureau of Labor Statistics projects employment in radiology will grow 5 percent from 2024 to 2034, which is higher than the average of 3% across all occupations. Data from Indeed provided to CNN also indicates there were more radiology jobs in 2025 compared to five years ago. Demand for imaging during the medical diagnosis process, along with an increased aging population, is likely driving the need for more radiology services, say the radiology experts who spoke with CNN. But that wasn’t always the thinking. Nobel Prize-winning computer scientist Geoffrey Hinton, also referred to as the godfather of AI, said in 2016 that “people should stop training radiologists now” because deep learning – a subset of AI that models how the human brain learns – would handle the job better in five to 10 years. Hinton said in an email to the New York Times last year that he spoke too broadly in those 2016 comments. Demehri recalls there being a sense of anxiety in the radiology field about AI replacing human roles around the 2015 and 2016 timeframe. Now, the technology is seen as a “second set of eyes,” he said. Pitfalls of overreliance Still, there are risks around bias and potential overreliance on AI, according to Chen. Unlike human radiologists, for example, AI can accurately predict a person’s race based on an X-ray, according to a 2022 MIT study, raising concerns about bias in diagnoses. Chen says he also worries about the temptation to make staffing decisions – such as replacing a doctor with a nurse or a subspecialist radiologist with a primary care doctor – if AI becomes advanced enough. That might work in some cases, but not for the majority of conditions that radiology is used for, like detecting cancer or deadly infections. “We have to understand that a lot of the performance of (the) algorithm comes from the fact that the automation output is reviewed by an expert,” he said. “And together, this collaboration, if you will, between the machine and the expert is what makes the improvement real.” cnn.com/2026/02/09/tec…

@mrjuliusrose @judyshel How's your portfolio doin?

kevin warsh is nowhere to be found judy shelton is everywhere to be found trump has eyes on you young lady. @judyshel