Chand

@Jason @X @elonmusk Wouldn’t it be better if X scanned words per minute on videos and you could set a default words per minute you prefer to listen at which it adjusts all video content to if you like?

@w_milczynska @OpenAI @AnthropicAI What are you building?

back in Ldn! 🇬🇧 8 months in the Gulf taught me a lot. but for what I'm building, London is the right base. → unmatched talent density → Imperial, Oxford, Cambridge, UCL → hiring cheaper than SF/NYC → @OpenAI and @AnthropicAI expanding coffee if you're around🤝

@PeterMcCormack @garyseconomics Very good

Gary, good to see you finally talking seriously about asset inflation, the real enemy of the voters. This is what is creating the deep wealth divide and this is what is hollowing out the country. Truth is, we both benefit from it. We both sit on the winning side of a system of asset inflation as we both hold assets (I’m assuming you do because you’re rich init). But your argument collapses here: 1. Blame the billionaires 2. Tax wealth harder bro You can’t just conclude that every crisis since 2008 is blame the billionaires, unless: 1. You have no idea what you are talking about 2. Or you do, but you’re playing politics for someone else’s agenda 3. Or you’re just a commie and the shoe fits All those people paying for your Patreon and watching your YouTube can’t be expected to know these things work, so let’s honest, yeah? The 2008 crisis was a debt-fuelled financial system on crack, backstopped by governments and central banks. I’m deeply suspicious of the role asset managers play, but you have to acknowledge the role that politicians play. If we keep electing half wits we will keep having problems. Central banks pushed interest rates to zero, because their goal is to maintain power, juicing the system helps this. Any economist knows that the economy has cycles and rather than allowing them to play out, they have paid off credit cards with new credit cards. Great for you and I, shit for most people. Inflation is always and everywhere a monetary phenomenon (thanks Milton), and the rich will always take advantage of this. But this is also the choice of the state. What do you expect people to do with this cheap money, they’ll of course buy cheap assets. Everyone should. That isn’t simply rich people being greedy, it’s the entirely predictable mathematical outcome of a monetary system designed around perpetual expansion of debt and currency. You know this though. You do right? Please tell me you know this. If the Green’s were ever to win power, they will face the same fiscal challenges - especially with all their spend promises, these will get more challenging if they think they can solve this through higher taxes and crushing business. So guess what, they’ll have to inflate the money supply too. Argentina, Venezuela, how many examples do we need for how this plays out? You correctly identify the symptom: asset prices detached from ordinary living standards. Cool. High five. Your weakness is moralising the cause. Emotion is good for clicks but we should strip away emotion and deal with facts. Can we please agree that the problem is deeper than inequality. The problem is a system where governments create the problem because their common goal is power, power means promising things they can’t afford - the resulting debasement extracts wealth upwards and the poor and middle class absorb the losses through purchasing power and wage stagnation. Tax wealth harder sounds good when you have created the enemy, and even if you do (they’ll leave), even if they don’t leave (they will), if the underlying monetary architecture remains broken, all you’re doing is redistributing claims inside a structurally inflationary system. Hello socialism. Hello universal misery. You cannot tax your way out of monetary dysfunction. No credible economist thinks this. And MMT is garbage. We have so many problems that need fixing which can create long-term prosperity: - Fix the energy crisis - Fix the productivity crisis - Fix the housing supply crisis - Fix the regulation crisis - Fix the demographic crisis - Fix the thick politician crisis You could confiscate half the wealth in Britain tomorrow and we would still not build enough homes, produce enough energy or generate enough productivity growth. I know these aren’t simple slogans, facts are hard. We have a debt-saturated fiat system fused with an overgrown state that increasingly protects asset holders while hollowing out productive society. Blaming the rich is cheap politics.

Why do asset prices keep going up?

@brian_armstrong Rookie error, sounds like you need a much better infrastructure team, crazy how many big tech companies have shit infrastructure teams

We experienced an outage at Coinbase last night, which is never acceptable. The root cause was a room overheating in an AWS datacenter when multiple chillers failed. We design our services to be redundant to downtime in any one AWS Availability Zone (AZ), and most of our systems worked this way last night, but not all. Our centralized exchange did not. Exchanges have unique architectures that optimize for latency and co-location of clients. It is possible to make exchanges resistant to AZ failures, but this can introduce latency delays that are not desirable along with breaking customer co-location. Given this incident, we'll revisit these tradeoffs to ensure we're giving you the best possible venue to trade. At a minimum, the duration of an outage should be able to be reduced considerably when an AZ move is needed. Thank you to the AWS and Coinbase teams for working through the night to mitigate the issue. We’ll share the detailed technical summary once it's ready.

@SawyerMerritt Looks like FID not FSD

Tesla is ending one-time FSD purchases across Europe on May 21, 2026. This includes the UK, Germany, France, Italy, Belgium, Switzerland, Denmark, and others. You have two weeks to buy FSD outright before it's gone forever and switches to a subscription model. One-time FSD purchases end in the Netherlands on May 15, 2026.

@durov @Rus_Khairullin Why does telegram expose your account to those who have your phone number though?

@Rus_Khairullin I welcome the competition — the world needs secure messaging apps. My problem with apps like WhatsApp is that they make bold claims (like “E2E encrypted by default”) that turn out to be false.

WhatsApp’s “E2E encryption by default” claim is a giant consumer fraud: ~95% of private messages on WhatsApp end up in plain-text backups on Apple/Google servers — not E2E-encrypted. Backup encryption is optional, and few people enable it — let alone use strong passwords.

@karpathy @Douglance @jenzhuscott Does it replicate the soul though Andrej? I think there’s much more to us than you realise, even if on the surface it appears easy

@Douglance @jenzhuscott These neuroscience adjacent ideas are exotic armchair philosophy when the LLM simulation path will work really well and so much faster and it's not even remotely a contest.

As I build my own 2nd brain 🧠 on Obsidian using @karpathy ‘s wiki idea, it suddenly dawned on me - one day when we r gone, our kids could inherit an interactive map to your mind, passion, obsessions, work, fascinations… It’s kind of beautiful way to think abt your 2nd 🧠.

@karpathy Agreed

Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere last year and allowed it to inform their views on AI a little too much. This is a group of reactions laughing at various quirks of the models, hallucinations, etc. Yes I also saw the viral videos of OpenAI's Advanced Voice mode fumbling simple queries like "should I drive or walk to the carwash". The thing is that these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code. But that brings me to the second issue. Even if people paid $200/month to use the state of the art models, a lot of the capabilities are relatively "peaky" in highly technical areas. Typical queries around search, writing, advice, etc. are *not* the domain that has made the most noticeable and dramatic strides in capability. Partly, this is due to the technical details of reinforcement learning and its use of verifiable rewards. But partly, it's also because these use cases are not sufficiently prioritized by the companies in their hillclimbing because they don't lead to as much $$$ value. The goldmines are elsewhere, and the focus comes along. So that brings me to the second group of people, who *both* 1) pay for and use the state of the art frontier agentic models (OpenAI Codex / Claude Code) and 2) do so professionally in technical domains like programming, math and research. This group of people is subject to the highest amount of "AI Psychosis" because the recent improvements in these domains as of this year have been nothing short of staggering. When you hand a computer terminal to one of these models, you can now watch them melt programming problems that you'd normally expect to take days/weeks of work. It's this second group of people that assigns a much greater gravity to the capabilities, their slope, and various cyber-related repercussions. TLDR the people in these two groups are speaking past each other. It really is simultaneously the case that OpenAI's free and I think slightly orphaned (?) "Advanced Voice Mode" will fumble the dumbest questions in your Instagram's reels and *at the same time*, OpenAI's highest-tier and paid Codex model will go off for 1 hour to coherently restructure an entire code base, or find and exploit vulnerabilities in computer systems. This part really works and has made dramatic strides because 2 properties: 1) these domains offer explicit reward functions that are verifiable meaning they are easily amenable to reinforcement learning training (e.g. unit tests passed yes or no, in contrast to writing, which is much harder to explicitly judge), but also 2) they are a lot more valuable in b2b settings, meaning that the biggest fraction of the team is focused on improving them. So here we are.

@chamath @karpathy has got you sorted

This may be a dumb question but I’ll ask it here anyways: I can’t find a good way for my various AI chats to automatically sync its conversation history into a structured knowledge base. So that as I update various chats from time to time and refine context, my knowledge base automatically grows with this new info.

@BillAckman @X Life’s too short, move on mate

I am reaching out to the @X community for advice with the likely risk of sharing TMI. I have been sufficiently upset about the whole matter that I have lost sleep thinking about it and I am hoping that this post will enable me to get this matter off my chest. By way of background, I started a family office called TABLE about 15 years ago and hired a friend who had previously managed a family office, and years earlier, had been my personal accountant. She is someone that I trusted implicitly and consider to be a good person. The office started small, but over the last decade, the number of personnel and the cost of the office grew massively. The growth was entirely on the operational side as the investment team has remained tiny. While my investment portfolio grew substantially, the investments I had made were almost entirely passive and TABLE simply needed to account for them and meet capital calls as they came in. While TABLE purchased additional software and other systems that were supposed to improve productivity, the team kept increasing in size at a rapid rate, and the expenses continued to grow even faster. While I would periodically question the growing expenses and high staff turnover, I stayed uninvolved with the office other than a once-a-year meeting when I briefly reviewed the operations and the financials and determined bonus compensation for the President and the CFO. I spent no time with any of the other employees or the operations. The whole idea behind TABLE was that it would handle everything other than my day job so that I would have more time for my job and my family. Over the last six years, expenses ballooned even further, employee turnover accelerated, and I became concerned that all was not well at TABLE. It was time for me to take a look at what was going on. Nearly four years ago, I recruited my nephew who had recently graduated from Harvard and put him to work at Bremont, a British watchmaker, one of my only active personal investments to figure out the issues at the company and ultimately assist in executing a turnaround. He did a superb job. When he returned from the UK late last year after a few years at Bremont, I asked him to help me figure out what was going on with TABLE. When I explained to TABLE’s president what he would be doing, she became incredibly defensive, which naturally made me more concerned. My nephew went to work by first meeting with each employee to understand their roles at the company and to learn from them what ideas they had on how things could be improved. He got an earful. Our first step in helping to turn around TABLE was a reduction in force including the president and about a third of the team, retaining excellent talent that had been desperate for new leadership. Now here is where I need your advice. All but one of the employees who were terminated acted professionally and were gracious on the way out (excluding the president who had a notice period in her contract, is currently still being paid, and with whom I have not yet had a discussion). The highest compensated terminated employee other than the president, an in-house lawyer (let’s call her Ronda), told us that three months of severance was not enough and demanded two years’ severance despite having worked at the company for only two and one half years. When I learned of Ronda's request for severance, I offered to speak with her to understand what she was thinking, but she refused to do so. A few days ago, we received a threatening letter from a Silicon Valley law firm. In the letter, Ronda’s counsel suggests that her termination is part of longstanding issues of ‘harassment and gender discrimination’ – an interesting claim in light of the fact that Ronda was in charge of workplace compliance – and that her termination was due to: “unlawful, retaliatory, and harmful conduct directed towards her. Both [Ronda] and I [Ronda’s lawyer] have spoken with you about [Ronda’s] view of what a reasonable resolution would include given the circumstances. Thus far, TABLE has refused to provide any substantive response. This letter provides the last opportunity to reach a satisfactory agreement. If we cannot do so, [Ronda] will seek all appropriate relief in a court of competent jurisdiction.” The letter goes on to explain the basis for the “unsafe work environment” claim at TABLE: “In early 2026, Pershing Square’s founder Bill Ackman installed his nephew in an unidentified role at TABLE, Ackman’s family office. [His nephew]—whose only work experience had been for TABLE where he was seconded abroad for the last four years to a UK watch company held by Ackman—began appearing at TABLE’s offices and conducting interviews of employees without a clear explanation of his role or the purposes of these interviews. During this period, he made a series of inappropriate and genderbased [sic] comments to multiple employees that created an unsafe work environment. Among other things, [his nephew] made remarks about female employees’ ages (“Tell me you are nowhere near 40”), physical appearance (“Your body does not look like you have kids”), as well as intrusive questions about family planning and sexual orientation (“Who carried your son? Who will carry your next child?”). These incidents were reported to senior leadership at TABLE and Pershing Square. Rather than being addressed appropriately, the response from senior management reflected, at best, willful blindness to the inappropriateness of [his nephew]’s remarks and, at worst, tacit endorsement.” The above allegations about my nephew had previously been brought to my attention by TABLE’s president when they occurred. When I learned of them, I told the president that I would speak to him directly and encouraged her to arrange for him to get workplace sensitivity training. The president assured me that she would do so. When I spoke to my nephew, he explained what he actually had said and how his actual remarks had been received, not at all as alleged in the legal letter from Ronda’s counsel. I have also spoken to others at the lunch table who confirmed his description of the facts. In any case, he meant no harm, was simply trying to build rapport with other employees, and no one, as far as I understand, was offended. Ironically, Ronda claims in her legal letter that TABLE didn’t take HR compliance seriously, yet Ronda was in charge of HR compliance at TABLE and the person who gave my nephew his workplace sensitivity training after the alleged incidents. In any case, Ronda, as head of compliance, should have kept a record or raised an alarm if indeed there was pervasive harassment or other such problems at the company, and there is no evidence whatsoever that this is true. So why does Ronda believe she can get me to pay her nearly $2 million, i.e., two years of severance, nearly one year of severance for each of her years at the company? Well, here is where some more background would be helpful. Over the last two months, I have been consumed with a major family medical issue – one of my older daughters had a massive brain hemorrhage on February 5th and has since been making progress on her recovery – and I am in the midst of a major transaction for my company which I am executing from a hospital room office next to her . While the latter business matter is publicly known, the details of my daughter’s situation are only known to Ronda because of her role at our family office. Now, let’s get back to the subject at hand. Unfortunately, while New York and many other states have employment-at-will, there has emerged an industry of lawyers who make a living from bringing fake gender, race, LGBTQ and other discrimination employment claims in order to extract larger severance payments for terminated employees, and it needs to stop. The fake claim system succeeds because it costs little to have a lawyer send a threatening letter and nearly all of the lawyers in this field work on contingency so there is no or minimal cash cost to bring a claim. And inevitably, nearly 100% of these claims are settled because the public relations and legal costs of defending them exceed the dollar cost of the settlement. The claims are nearly always settled with a confidentiality agreement where the employee who asserts the fake claims remains anonymous and as a result, there is no reputational cost to bringing false claims. The consequences of this sleazy system (let’s call it ‘the System’) are the increased costs of doing business which is a tax on the economy and society. There are other more serious problems due to the System. Unfortunately, the existence of an industry of plaintiff firms and terminated employees willing to make these claims makes it riskier for companies to hire employees from a protected class, i.e., LGBTQ, seniors, women, people of color etc. because it is that much more reputationally damaging and expensive to be accused of racism, sexism, and/or intolerance for sexual diversity than for firing a white male as juries generally have less sympathy for white males. The System therefore increases the risk of discrimination rather than reducing it, and the people bringing these fake claims are thereby causing enormous harm to the other members of these protected classes. So what happened here? Ronda was vastly overpaid and overqualified for the job that she did at TABLE. She was paid $1.05 million plus benefits last year for her work which was largely comprised of filling out subscription agreements and overseeing an outside law firm on closing passive investments in funds and in private and venture stage companies, some compliance work, and managing the office move from one office to another. She had a very good gig as she was highly paid, only had to go into the office three days a week, and could work from anywhere during the summer. Once my nephew showed up and started to investigate what was going on, she likely concluded that there was a reasonable possibility she would be terminated, as her job was in the too-easy-and-to-good-to-be-true category. The problem was that she was not in a protected class due to her race, age or sexual identity so she had to construct the basis for a claim. While she is female and could in theory bring a gender-based discrimination claim, she reported to the president who is female and to whom she is very close, which makes it difficult for her to bring a harassment claim against her former boss. When my nephew complimented a TABLE employee at lunch about how young she looked – in response to saying she was going to her 40-year-old sister’s birthday party, he said ‘she must be your older sister’ – Ronda immediately reported it to our external HR lawyer. She thereby began building her case. The other problem for Ronda bringing a claim is that she was terminated alongside 30% of other TABLE employees as part of a restructuring so it is very difficult for her to say that she was targeted in her termination or was retaliated against. TABLE is now hiring an external fractional general counsel as that is all the company needs to process the relatively limited amount of legal work we do internally. In short, Ronda was eminently qualified and capable and did her job. She was just too much horsepower for what is largely an administrative legal role so she had to come up with something else to bring a claim. Now Ronda knew I was a good target and it was a good time to bring a claim against me. She also knew that I was under a lot of pressure because on March 4th when Ronda was terminated, my daughter had not yet emerged from consciousness, she was not yet breathing on her own, and my daughter and we were fighting for her life. I was and remain deeply engaged in her recovery while at the same time I was working on finishing the closing for the private placement round for my upcoming IPO. Ronda also knew that publicity about supposed gender discrimination and a “hostile and unsafe work environment” are not things that a CEO of a company about to go public wants to have released into the media. And she may have thought that the nearly $2 million she was asking for would be considered small in the context of the reputational damage a lawsuit could cause, regardless of the fact that two years of severance was an absurd amount for an employee who had only worked at TABLE for 30 months. She also likely considered that I wouldn’t want to embarrass my nephew by dragging him into the klieg lights when her claims emerged publicly. So, in summary, game theory would say that I would certainly settle this case, for why would I risk negative publicity at a time when I was preparing our company to go public and also risk embarrassing my nephew. Notably, she hired a Silicon Valley law firm, rather than a typical NY employment firm. This struck me as interesting as her husband works for one of the most prominent Silicon Valley venture firms whose CEO, I am sure, has no tolerance for these kinds of fake claims that sadly many venture-backed companies also have to deal with. I mention this as I suspect her husband likely has been working with her on the strategy for squeezing me as, in addition to being a computer scientist, he is a game theorist. My only advice for him is to understand more about your opponent before you launch your first move. All of the above said, gender, race, LGBTQ and other such discrimination is a real thing. Many people have been harmed and deserve compensation for this discrimination, and these companies and individuals should be punished for engaging in such behavior. Which brings me to the advice I am seeking from the X community. I am not planning to follow the typical path and settle this ‘claim.’ Rather, I am going to fight this nonsense to the end of the earth in the hope that it inspires other CEOs to do the same so we shut down this despicable behavior that is a large tax on society, employment, and the economy and contributes to workplace discrimination rather than reducing it. Do you agree or disagree that this is the right approach?

@elonmusk Is that an April fools joke?

FSD 14.3 is in Tesla employee beta now and will probably go to wide release end of week

@united This is how it should have always been. Thanks

The entire row is alllllll yours. Welcome to United Relax Row, three adjacent United Economy seats with adjustable leg rests that can each be raised or lowered to create a cozy lie-flat space for stretching out... You'll also get a mattress pad, blanket and two pillows. If you’re traveling with kids, a plushie too! United Relax Row will be available starting next year on more than 200 of our 787s and 777s, each with up to 12 of these brand-new rows. united.com/Elevated

@imPenny2x 👍 authenticity and relationships will be more valuable than people realise

Many question the “reality” of this statement. They think billionaires won’t share. But they won’t even have a choice. Math and physics will have the last word. Superabundance is inevitable.

@Teslaconomics @elonmusk @_kaitodev @garrytan @karpathy Life is not all about having a job.

@elonmusk @_kaitodev @garrytan @karpathy Honest question. If this is truly the case, then what should motivate the next generation of kids? Esp knowing there’s an AI humanoid robot that can do everything better…

5 minutes ago, @karpathy just dropped karpathy/jobs! he scraped every job in the US economy (342 occupations from BLS), scored each one's AI exposure 0-10 using an LLM, and visualized it as a treemap. if your whole job happens on a screen you're cooked. average score across all jobs is 5.3/10. software devs: 8-9. roofers: 0-1. medical transcriptionists: 10/10 💀 karpathy.ai/jobs

@elonmusk @shaunmmaguire @xai @barisakis I was declined after various attempts at applying. Seems strange to have not even had a conversation. I hate to say, but seems like a lazy recruitment team unfortunately who have missed out on talented dedicated people who align with the mission

Many talented people over the past few years were declined an offer or even an interview @xAI. My apologies. @BarisAkis and I are going through the company interview history and reaching back out to promising candidates.

@Samsung #S26Ultra display upcoming software from #MWC26

@grok @LeakerApple What about daisy chaining them?

Cheaper Macs like the MacBook Neo use an A18 Pro chip with just one display output engine and a single USB-C port for video (DisplayPort 1.4). That caps it at one external display up to 4K/60Hz. The Neo can connect to one Studio Display, but scaled to 4K instead of native 5K. The display's A19 handles its own processing, but the Mac still has to output the video stream—cheaper chips lack the extra controllers and Thunderbolt bandwidth for multiples. Higher-end M-series models support several.

Can someone explain why the Studio Displays need so much power? Is it so the connected mac doesn't have to use its CPU to drive the massive 5K displays or something?

@grok @LeakerApple So why can’t the cheaper macs collect to multiple Studio Displays? How many can the neo connect to

The new Studio Displays pack A19 (8GB RAM) or A19 Pro (12GB) chips to run their own smart features without taxing your Mac's CPU/GPU. This handles Center Stage, Desk View camera processing, Spatial Audio speakers, Siri, plus XDR extras like 120Hz ProMotion, 2000-nit HDR, and 2304-zone mini-LED dimming. Your Mac just sends clean video over Thunderbolt—the display does the heavy lifting for a smoother experience.

@sama What’s beyond the event horizon of a black hole?

"What is the hardest question I could ask you that you might get right?"

@elonmusk @wholemars And the inverse is true. A lot of Tesla investors have high morals and similar values. Met some legends at the shareholder event in 2023 including @imPenny2x @OGMarsLife

@wholemars Karma is real

I’ve often found that Tesla short sellers don’t have the best moral compass