Kim Nilsson @NoSubstitute

SPOGOU - #VIA20 #GoogleEI Pitch - Kim Nilsson youtu.be/ITGNmwVfU6Y via @YouTube - SPOGOU is my Google Certified Innovator project, a free open source Google Apps Script tool. It requires little to no programming skills to use. Will only get better. :-) github.com/NoSubstitute/S…

The Iranian navy, which has been destroyed eight times, closed the Strait of Hormuz again, because the United States for the seventh time won the war that wasn’t a war, so the United States can open the Strait of Hormuz that was open before the not war. The not war that started to get the uranium that was completely obliterated, so that the Iranians can’t build the nuclear bomb that they weren’t building for the not war that the United States started. Then the United States which has nuclear weapons threatening to use nuclear weapons to prevent Iran from having nuclear weapons because having nuclear weapons is dangerous. If the United States saw what the United States is doing in the United States, the United States would invade the United States to liberate the United States from the tyranny of the United States.

Hypothetical question: If a President of the USA is a secret Russian asset, what would he do to help Russia? ChatGPT: Interesting thought experiment—and a useful way to think about incentives and power. If someone in that position were secretly acting in another country’s interest, the key wouldn’t be dramatic, obvious betrayals. It would be subtle, deniable, and cumulative. First, they’d likely undermine alliances quietly. The United States’ biggest strategic advantage is its network—especially NATO. So instead of openly pulling out, they might question its value, delay commitments, create distrust among members, or signal unreliability. Even small cracks weaken collective defense. Second, they could shift foreign policy in ways that benefit Russia without looking extreme. That might mean softening sanctions, slowing military aid to countries Russia opposes (like Ukraine), or reframing conflicts to reduce U.S. involvement. None of that needs to look like “helping Russia”—just “putting America first.” Third, damage internal cohesion. A divided country is less effective abroad. Amplifying polarization, discrediting institutions (courts, elections, intelligence agencies), or constantly creating internal crises reduces the ability of the U.S. to act strategically. That’s something adversaries historically benefit from. Fourth, reshape leadership and bureaucracy. Appointing people who are inexperienced, loyal over competent, or sympathetic to certain narratives can gradually shift how decisions are made. Over time, that changes policy outcomes without needing explicit orders. Fifth, control the narrative. Public opinion matters in democracies. Repeating talking points that align with Russian interests—questioning support for allies, portraying adversaries of Russia as corrupt or unworthy—can steer public sentiment in a favorable direction. Finally, they’d avoid anything blatantly illegal or provable. The whole strategy would depend on plausible deniability. If it’s obvious, it fails. The big picture: influence at that level isn’t about one shocking act—it’s about slowly tilting the system so that, over time, outcomes consistently benefit the other side.

🇬🇧 The first major assessment of the UK's Online Safety Act is out. Turns out kids are fooling the age checks by drawing moustaches on their faces. "I did catch my son using an eyebrow pencil to draw a moustache on his face, and it verified him as 15 years old." Mum of a 12-year-old, in a new report from Internet Matters, the UK's leading online-safety NGO. That single line tells you almost everything you need to know about how the UK's Online Safety Act is going. This is the law that: 🔴 Forced UK platforms to demand government IDs, facial scans, and credit-card checks from adults to access ordinary websites 🔴 Drove a 1,800%+ spike in VPN downloads the week the porn-site age checks went live in July 2025 🔴 Pushed millions of users into handing biometric data to private third-party verification vendors 🔴 Sits at the front of a global wave: Greece's anonymity ban, France's "VPNs are next" comments, Utah's VPN crackdown, and the EU's 27-state rollout deadline of December 2026 The headline numbers from the assessment: 🔴 46% of children say age checks are easy to bypass. Only 17% say they are difficult. 🔴 32% of children have already bypassed them in the past two months 🔴 49% of children still report experiencing harm online in the past month The bypass methods kids reported, in their own words: 🔴 Drawing on facial hair with eyebrow pencil to fool facial age estimation 🔴 Holding up a video game character's head turning during the face-scan 🔴 Submitting a video of a different person's face entirely 🔴 Using a parent's ID (often with parental consent) 🔴 Entering a fake birthday (still works on most platforms) 🔴 Using someone else's login or device 🔴 In a small minority of cases, VPNs One 12-year-old girl explained the system to researchers: "Every time I go live on TikTok, it tells me I have to be 18, but when the AI detects that I'm not 18 they ban me. But they only ban me for 10 minutes and then I can go live again." That is the entire enforcement model. A 14-year-old summed up the broader picture: "It's not practical because the more you restrict it, the more people are going to want to get past that age restriction." A 16-year-old, more bluntly: "I think it's a great idea in theory and I applaud its intentions, but I don't see how that's feasible, because kids will always find a way." Even when verification works, it works against the children. A 12-year-old boy on Roblox: "I put my face in and I got 15 when I'm 12, so I'm chatting with people older than me when I shouldn't be." A 13-year-old non-binary child: "Adults can very easily use a face they searched on the internet to trick it into thinking you're someone you're not, so there might be adults in kids' age groups trying to groom them." Recent reporting confirms exactly that. Underage Roblox accounts are now being sold online to predators precisely because they bypass the new "safety" measures. One detail in the report stops you cold. Multiple children described being unintentionally exposed through their feeds to the assassination of Charlie Kirk. A 14-year-old: "I saw it on Snapchat. I broke down into tears and then told my mum immediately." Violent content, racist content, content promoting unrealistic body types: all explicitly prohibited under the Children's Safety Codes. All still landing in feeds at scale. Parents told researchers about the day-to-day reality of trying to enforce the rules at home. A father of a 14-year-old: "What you'll find now is that the kids know more than we know in terms of how to disable [parental controls]. We've got the parental controls on, but they probably unlock them." A mother of a 13-year-old: "We do what we can, but our kids are all clever and savvy and they can get around stuff." A mother of a 12-year-old: "I can put all the checks and measures in, and I can be keeping an eye open on what she's watching, listening to, who she's chatting to. And then she could go to a house down the road and visit somebody whose parents don't care, and they've got zero checks and measures." Both children and parents expressed real concerns about handing over biometric data to verification platforms they do not trust. One father warned: "Kids don't know the difference between a genuine website and a website that isn't genuine. If all websites have facial verifications and they go on a website that is not genuine, their face and their documents could be used to do illegal stuff." The father is right. The Discord vendor breach in October 2025 already exposed roughly 70,000 government IDs uploaded purely for age verification. The EU's own age verification app was reportedly hacked within minutes of launch. The report's most uncomfortable finding sits inside the parental data. 26% of parents are not just aware their kids bypass age checks, they are actively complicit. Some logged into their child's account with their own ID to "go live" on TikTok. Others approved circumvention so their child could play a specific game. The reasoning is rarely malicious. Parents told researchers they only help when they personally judged the activity safe. But the structural problem is fatal: a verification system that treats parents as the last line of defence collapses the moment parents themselves become the bypass. Even children who follow the rules end up disadvantaged by them. A 15-year-old: "There are websites that are support websites to help with things such as eating disorders and suicide, and they've all been censored." A 12-year-old: "Before you could talk to anybody, but they added age group limits so you can only talk to people in your age group. So if my friends are younger or older than me I wouldn't be able to talk to them." The blunt instrument of age-gating breaks legitimate connection and support without measurably reducing harm.

Talking only with the White House is a part of Putin's attempts to delegitimize Ukraine as a sovereign nation, and to present himself as a big boss who only talks with other big bosses. This mentality is also why Russia's war is against the free world, not just Ukraine.

BREAKING: SOUNDS OF SILENCE — Senate hearing goes deadly quiet as Trump’s federal judicial nominees REFUSE to admit third term is illegal. . Donald Trump is nominating people to lifetime federal judgeships who won't confirm that he can't run for a third term when they come before the Senate for their approval hearings. Let that sink in. Senator Chris Coons of Delaware asked what should be the easiest constitutional law question in American history at a Senate Judiciary Committee hearing this week. He asked Trump's judicial nominees about the 22nd Amendment. The first nominee, John Marck, said that his career had been in criminal prosecution and that he hadn't had occasion to use that particular amendment. A federal judicial nominee. Unfamiliar with the 22nd Amendment. Seeking a lifetime appointment to interpret the Constitution. Another candidate eventually offered that it "deals with the two-term limitation." Correct. Gold star. Coons then asked the simple follow-up: is President Trump eligible to run for president again in 2028? Marck's response was a masterpiece of evasion: "Without considering all the facts and looking at everything, depending on what the situation is, this to me strikes as more of a hypothetical." Coons was patient. He walked Marck through it like a kindergarten teacher explaining why you can't eat paste. Has Trump been elected president twice? "President Trump has been certified the President of the United States two times." Is he eligible to run for a third term? "I would have to review the actual wording of it." A man seeking a lifetime federal judgeship needs to review the actual wording. Of the 22nd Amendment. Which is 61 words long. Coons then turned to the full panel and asked if anyone — anyone — was willing to simply state that the Constitution of the United States bars Trump from seeking a third term. A heartbreakingly long silence ensued. He asked again. Anyone willing to apply the Constitution by its plain language? More ominous silence. Nobody. Not one of Trump's judicial nominees would say out loud, under oath, in a Senate hearing, that the 22nd Amendment means what it plainly says. This isn't ignorance. These are lawyers. They know what the 22nd Amendment says. They know Trump has been talking openly about a third term. And they calculated — correctly, based on what happens to people who cross this president — that telling the constitutional truth was more dangerous than staying silent. The frightening thing is that these are the people who will be interpreting your rights for the next 30 years. Please like and share this post if you think federal judges should be willing to say the Constitution means what it says — even when the president doesn't want to hear it.

No, "AI" doesn't lie. They are just wrong. LLMs do not know what is true, they just present a probable response. Too often it's not factual, and the LLM companies know this and still market the tools as true helpers, desperately trying to claw some money back.

Four days ago, I wrote that after every Trump-Putin phone call, something deranged follows within weeks. I said mark the date. I said the clock is ticking. I was wrong. It took seventy-two hours. Allow me to recap what the leader of the free world has done to his closest allies since that cosy ninety-minute phone call with a man who poisons people in their driveways. Germany: 5,000 troops withdrawn. More promised. The Army’s Long Range Fires Battalion, scheduled to deploy to Europe, quietly cancelled. Germany, which actually met its NATO spending targets, which opened its bases and airspace to American operations, which did everything Trump asked, got punished anyway. Because its chancellor had the audacity to point out that Iran was humiliating Washington at the negotiating table. He was right. That was the problem. Italy: threatened with troop withdrawal because, in Trump’s words, Italy “has not been of any help.” Italy, a founding NATO member. Italy, which hosts tens of thousands of American troops and several critical US military installations. Useless, apparently. Spain: “horrible. Absolutely horrible.” Spain’s crime was refusing to let the United States use Spanish bases and airspace to bomb Iran. A sovereign decision by a sovereign ally. Described by the President of the United States as horrible. The European Union: 25% tariffs on cars and trucks, announced in the same week as the troop withdrawals. Germany builds cars. This was not a coincidence. And through all of this, Vladimir Putin got a ceasefire proposal endorsed, a nuclear diplomacy role handed to him on a plate, and not a single harsh word. Four days ago I predicted one unhinged announcement, one ally humiliated, and one idea so catastrophically stupid that the national security apparatus would spend a weekend trying to undo it. We got four allies humiliated, two economic attacks, and a full military retreat from the continent America spent eighty years promising to defend. I would say I am surprised. But I wrote it down in advance. Which makes this less a prediction and more a schedule. Stay connected, Follow Gandalv @Microinteracti1

2022: “Stop overreacting, they won’t overturn Roe.” They did. 2023: “Stop overreacting, they won’t let women die rather than get an abortion.” They did. 2024: “Stop overreacting, they won’t arrest women for miscarriages.” They did. 2025: “Stop overreacting, they won’t turn women into incubators.” They did. 2026: “Stop overreacting, they won’t attack mifepristone.” They did, today. Now: “Stop overreacting, they won’t go after birth control next.” They will.

Jag har arbetat som lärare i 25 år. Varje läsår ska lärare lägga 104 timmar på fortbildning, 104 timmar eller 13 dagar. Under mina 25 år skull jag alltså haft tillgång till 325 dagar eller 2600 timmar fortbildning.

May the fourth be with you

Americans don't understand that we did not lose trust in Trump. We never trusted him. We lost trust in the American people not to elect people like Trump & lost trust in US institutions to reign a president like Trump in if he hurt US allies. Both people + institutions failed.

If there was one single line of inquiry in last weeks oversight hearings on the Iran War this was it from Rep Adam Smith. His entire line of questioning was absolutely on the money, but this particular clip exposes the complete lack of preparedness other than to drop thousands of tons of ordinance, on the assumption that the worlds top exponent of asymmetric warfare would fold. Hegseth’s inability to grasp the very basics of armed conflict is frankly astounding. Time after time the US military has faced an insurgent enemy and come up short EVERY TIME. If war was a competition for who can blow the most money and drop the most bombs, the U.S. would be world champions, but it’s not. Arrogance and hubris don’t win wars. Strategic planning and anticipation of events win wars. Alienating allies then assuming they will join a failed war is beyond arrogant. As pointed out by Rep Smith NATO is a defensive alliance, not a supporting actor for a US extortion attempt. Trump has decided now to draw down 5000 US troops from Germany as punishment for criticism of this failed war. This does NOT remove protection from Europe, it merely reduces US force projection in the region limiting global reach for Middle East operations. 🎥 TikTok - vm.tiktok.com/ZNRp8GrQX/

Good. It was always a bad idea to have students do assignments outside the classroom, but not until everyone ( = the poor) could have someone else (LLMs) do their work for them was it defined as a problem.

Something a lot of people don't see. Trump thinks US troops in Germany are there to protect Germany. They're not. They're there because the US needs the bases to be able to carry out US operations beyond the north American continent. Trump doesn't understand this basic fact.

SHiFT code for three Golden Keys in Borderlands 4: T96J3-SFRH3-56BJC-3TTTJ-ZBJSB Redeem in game or at shift.gearbox.com. Expires 5/5. Good luck, and happy looting!

Senator @SenMarkKelly asks Pete Hegseth if he stands by his statement that he would provide no quarter and no mercy to the enemy. Hegseth refuses to answer a simple “yes” or “no” question. Senator Kelly: “I’m going to give you one more chance to address a question here… Your quote was ‘we will keep on pushing, keep advancing, no quarter, no mercy for our enemies,’ and yesterday you did not clarify if you stand by this statement.” Hegseth: [non-answer] Senator Kelly: “You are the Secretary of Defense. The things you say matter and your response here, right now, makes it clear to the American people exactly why you are not right for this job.”

🔥🔥🔥The new version of Swampcore 2.0.0.5 has been built ⚡️⚡️⚡️ github.com/Swampthing-Swa… #LowCapGem #Crypto #CPUMining #Altcoins #altseason #cryptocurrency #DeFi #NFT #bullrun #tothemoon #cryptomonster #cpucoin #RWA #Airdrop #newtoken

I’m sorry, I was reliably told this was going to be privately funded.

Nvidia just admitted that "AI efficiency" is a LIE. Every major tech company is doing the same thing right now: Firing humans and replacing them with AI to "cut costs." 92,000 tech workers laid off in 2026 so far. Every single earnings call sounds the same: "AI is driving efficiency." But the VP of Applied Deep Learning at Nvidia, the company that literally SELLS the AI infrastructure, just told Axios: "For my team, the cost of compute is far beyond the costs of the employees." The man whose entire job is making AI work admitted that AI costs his company MORE than the humans it's supposed to replace. And he doesn't work at some struggling startup. We're talking about the most valuable company on Earth. An MIT study backs this up too: Researchers analyzed whether AI could actually replace human workers at a competitive cost and found that AI automation only makes financial sense in 23% of jobs. In the other 77%, humans are still cheaper. So companies are firing cheap labor and replacing it with expensive labor, then telling shareholders it's "innovation." But it gets even WORSE... Uber just revealed that they burned through their ENTIRE 2026 AI budget in 4 months. Their CTO said: "I'm back to the drawing board because the budget I thought I would need is blown away already." What happened is that Uber gave their engineers access to AI coding tools and encouraged them to use them as much as possible. They even built internal leaderboards ranking engineers by how many AI tokens they consumed, basically gamifying their own budget crisis without realizing it. By March, 95% of Uber's engineers were using AI tools monthly. 70% of all committed code was coming from AI. Monthly API costs per engineer hit $500 to $2,000. One software engineer in Stockholm told the New York Times: "I probably spend more than my salary on Claude." A human being now costs LESS than the AI tool they use to do their job. And Uber isn't some edge case. Big Tech has announced $740 billion in AI capital expenditures this year alone, up 69% from 2025, according to Morgan Stanley. Meanwhile the Yale Budget Lab says there is NO widespread data showing AI is actually displacing jobs or improving productivity at scale. So follow the money: Companies fire humans ↓ Stock goes up because "AI efficiency" ↓ Those same companies spend MORE on AI than they saved on salaries ↓ That money flows to Nvidia, Anthropic, OpenAI, and Microsoft ↓ Those companies use the revenue to justify their own insane valuations ↓ Everyone books growth ↓ But nobody's actually saving money McKinsey projects total AI spending will hit $5.2 TRILLION by 2030. The biggest wealth transfer in modern history is happening right now, and it's not from workers to companies. It's from companies to AI infrastructure providers. Every dollar "saved" on layoffs is being spent twice over on compute, tokens, and data centers. Nvidia posted $31.9 billion in profit last quarter. And somebody is paying that bill - the same companies telling their employees that AI made them "redundant." The entire narrative is a shell game: CEOs get to announce layoffs, Wall Street rewards them with a stock bump, and then the real cost shows up three months later when the AI budget explodes and nobody connects the two events. What's your take on this?

What did Charles actually do? He praised NATO in front of its loudest critic. He championed climate action in front of a climate denier. He called for interfaith dialogue during an administration that has banned citizens from Muslim-majority countries. He praised checks and balances on executive power to a room full of lawmakers who have been unable to exercise them. He referenced the Middle East crisis that is currently straining the alliance he was there to celebrate. He defended the Royal Navy after Trump publicly insulted it. And he did all of this while receiving standing ovations, bipartisan laughter, and a dinner invitation.