与「quit」相关的搜索结果

A lovely song and a lovely video can still be completely wrong for each other. That’s why Montage Studio caught my attention on @termix_ai It takes a brief, plans the shots, hires other agents for the storyboard, music and video, then edits everything into a finished piece. I’d be paying for someone to make those choices work together. Otherwise I’ve bought three nice files and accidentally become the project manager. For creators, that’s a useful way to judge these services: how much work is actually left when the delivery arrives? I’d quite like to receive the video and remain peacefully uninvolved in its staffing issues.

Ever seen cherries labelled "J," "JJ" or "JJJ" in a Chinese supermarket? Here's what it means. In China, imported sweet cherries are called "che li zi," a transliteration of the English word "cherries." They're sold by size grade, and the number of J's tells you the diameter. Based on common labels on Chinese e-commerce platforms:
 J: about 26 to 28 mm
JJ: about 28 to 30 mm
JJJ: about 30 to 32 mm
4J: about 32 to 34 mm Each extra J adds roughly 2 mm, and can add quite a bit to the price. Right now is Chilean cherry season in China. Chile's summer is China's winter, so the first air shipments arrive in late October, with peak supply in December and January, just in time for New Year and Lunar New Year gifting. China is Chile's biggest cherry customer by far: according to 21st Century Business Herald, China has bought more than 90% of Chile's cherry exports for seven years in a row. Does anywhere near you grade fruit by size like this? 
#cherries# #Chile# #agriculture# In-depth reports at

Aishah Sofey had to reassure Mr. Kim and her chat that she wasn’t quitting streaming and that she still loved it after Mr. Kim approached her at TwitchCon, saying he was about to text her and offer her some advice after seeing the clips of her talking about quitting. “That’s so nice. I’ve had a lot of this. I’m not quitting; I love it, and I’m here having so much fun.”

I have a major result to share. I’ve found conclusive forensic evidence that the top 4 Chinese AI labs—DeepSeek, Moonshot, MiniMax and Ant Group—have built their newest models on NVIDIA’s most advanced Blackwell chips, which are barred from export to China. This sounds insane, but I discovered that almost every AI model carries a hidden signature of the GPU that trained it. When a model is first set up, the starting values of its weights are laid out in a pattern that depends on the exact GPU. Each combination of GPU and seed number produces a unique pattern—a sort of fingerprint of the hardware used to create the model. Traces of that pattern survive training into the published model. Again, this evidence isn’t based on any insider information or leaking. It’s based on a forensic analysis of the model weights released by the companies themselves. I searched more than six trillion combinations of chip layout and seed number and matched them to open-weights models. In doing so, I found conclusive evidence that six Chinese AI models—including DeepSeek-V4-Pro, Kimi K3, and MiniMax-M3—were initialized on NVIDIA Blackwell systems. Four of the models match Grace Blackwell, the GB200 and GB300 parts in NVIDIA’s flagship liquid-cooled rack-scale systems. I then verified these results on real hardware. Running unmodified PyTorch with the seeds I’d recovered, a Blackwell B300 reproduced DeepSeek-V4-Flash’s untouched starting weights bit for bit, and a rented GB200 reproduced Kimi K3’s to a correlation of 0.999995. A Hopper H100 reproduced none of DeepSeek-V4-Flash’s, and changing the seed by one broke the match. (DeepSeek’s seed is 953049583 by the way.) The method also was verified to match 24 known open-weights models to the hardware that developers said they used. It is exceedingly unlikely that these results are a coincidence. Across six trillion combinations, the best accidental match should reach only about 8 sigma (i.e., eight standard deviations above what random chance would produce). The real matches range from 49 to 1,385 sigma, and even the weakest single test hits 20. These were data-center-scale training runs. With some analysis of release schedules and model details, I estimate that the largest, Kimi K3 and DeepSeek-V4-Pro, used 2,000 to 3,000 Blackwell GPUs each. Clusters of this size cost on the order of $150 to $200 million each to buy, and across these labs alone would add up to more than half a billion dollars of export-controlled GPUs, not counting experimental compute or otherwise. It’s quite likely that we see multi-billion dollar expenditure on export-controlled GPUs. I am highly confident in this result, and it has been independently verified by senior researchers at OpenAI and Anthropic. You can read the full report at There is much more I’ve identified about these models through other forms of checkpoint forensics like this, and will have more to share soon.

MICROSOFT'S OWN SERVERS STARTED DROPPING OFFLINE — 128,874 OUTLOOK OUTAGE REPORTS — IN ORDER: → 12:54pm ET, Nov 12 — Microsoft investigates: users can't get into Exchange Online mailboxes in the Americas, via multiple connection methods → 1:07pm ET — Microsoft says it may hit users in any region — not just the Americas → 1:09pm ET — Outlook outage reports peak at 128,874 — Teams and Copilot reports climb → 2:12pm ET — Microsoft pauses all deployments → 2:31pm ET — servers are unexpectedly down, the rest are STRAINING By 2:50pm ET, servers were failing health checks. Not a traffic surge. Not a rush of users. Microsoft's own machines quit — and the whole workday waited. That's the sequence. And the app list in that outage tells you everything about what this is actually about: → The work inbox → The AI assistant inside Office → The office suite with 321 million active users This isn't just an email outage. It's a world office on wheels — and it stalled because the fleet wasn't done failing. 2:50pm ET: Microsoft restarts all affected servers. When Microsoft names what knocked those servers out, you'll wish you'd followed me.

Mi jefe me permitió trabajar desde casa para cuidar a mi hijo por las tardes. Estuve meses cumpliendo todos mis objetivos. De pronto, un día RRHH me llamó para QUITARME EL TELETRABAJO. Pregunté por qué, me enseñaron un mensaje de mi compañero y...

Jensen Huang is effectively OUT of NVIDIA🚨 Man His wife is 65 years 🇺🇸 They have been married for 41 years. As early microchip designers, she reportedly earned more money She totally left engineering work to raise their two children while Jensen Huang built Nvidia She was one of only three women in a class of 250 electrical-engineering students at Oregon State University when she and Jensen met. Jensen was 17 years when he walked up to the 19 year old Lori (his wife) and asked "Do you want to see my homework?" He promised that if they studied together every Sunday she would get straight A's, turning homework sessions into weekly dates. He also told her he would be a CEO by age 30. A promise he kept when he co-founded Nvidia in 1993. Jensen has repeatedly called meeting her "the most important, single event of Oregon university, and of my life" They married in 1985, the same year she graduated with her electrical-engineering degree. In 2022 the couple gave $50 million to Oregon State University (the campus where they met) to create a major innovation complex named after both of them. Jensen has said he does "zero percent" of his own shopping and that Lori (with their daughter) chooses his clothes, including the signature black leather jacket. He has publicly credited her with being "part of Nvidia every step of the way" and with handling the personal and financial details of their life. It's quite sad what is happening currently and how shattered Lori Huang must be.

Our message to Nvidia's board: Do not fire Jensen Huang. There is no clear replacement for Jensen Huang. We are confident that his departure would ultimately be a net negative for Nvidia, its shareholders, and the AI Revolution. First, take a look at the data. History also suggests that removing a successful CEO will come with a significant cost. A study of 187 forced CEO departures from S&P 1500 companies found that removing outperforming CEOs resulted in negative long-term stock returns. This case would be no different, in our view. Jensen Huang is the definition of an outperforming CEO. Nvidia's board must not make a decision in the heat of the moment. The board should take the time to conduct a thorough investigation and consult with shareholders, with a strong emphasis on the latter. Quite literally, Nvidia's board should convene a special shareholder meeting and hold an advisory vote on this decision. This is the most consequential CEO controversy in world history. Shareholders deserve a say. In addition, Nvidia's stock, $NVDA, is now down -35% in 26 trading days, nearly half of which is a result of the recent scandal. We believe Jensen Huang's potential removal as CEO is now ~80% priced in. Why take an action with massive downside potential when the market has already priced in much of that risk? The downside of retaining Huang may be limited, while the potential upside is tremendous. Lastly, history shows that retaining Jensen Huang could still lead to a favorable outcome. In 2019, Amazon retained Jeff Bezos as CEO after his extramarital affair became public, and the company's stock subsequently surged +108% by 2021. Personal misconduct should not be ignored, but it must also be distinguished from corporate wrongdoing and weighed against the consequences of removing an executive who is instrumental to the company's success. We believe Jensen Huang is an irreplaceable part of Nvidia and the AI Revolution more broadly. Once the dust settles, firing Jensen Huang would prove to be a costly mistake. It is time to pause and consult your shareholders.

overheard from friends talking about AI in China, and it’s very alarming - AI short films went massive in China market because of how good the video models are now - the first wave of people who mastered using AI to generate short films and comics made quite some money because they could produce a lot more content than traditional workflows - but within just a few months, everybody and their mom could make equally good short films because all the expertise could be written in a markdown file - when everyone’s more productive, no one actually has an advantage and it’s a race to the bottom. very quickly it became impossible to make money, and everyone’s busier than they were without AI - the only one making money now is companies like bytedance who owns user demand and distribution. they sell ads to creators who pay to get traffic, and eventually ad spend became 80% of those creators’ operating expense, while AI tokens is less than 5% so what are the problems here? 1. there’s no moat if you are creating anything with AI if a human is really good at something, and it’s hard to find more humans who can do the same, they can leverage the scarcity of their skill to get paid very well but if AI is good at something, it will be infinitely replicated, so there’s no scarcity hence you can’t really expect a sustainable business by creating anything with AI 2. more creators created more content people actually liked. that’s a good thing but the economical benefit of that all got absorbed by the distribution platforms there’s a famous chinese poem 遍身罗绮者，不是养蚕人 - it basically says people who dress well aren’t the people making dresses. that’s exactly what’s happening here if our society doesn’t figure out a better way to distribute wealth, AI will help billionaires become trillionaires while average people become more exhausted than ever

we’ve been a little quiet lately, but that doesn’t mean we’ve stopped building. quite a bit has shipped on antimatter. you can now find cheaper models that match the measured quality of the ones you’re already using, with potential savings surfaced directly in your dashboard and billing. we’ve also introduced model price alerts, optional daily email updates and a public changelog. less noise. more shipping. back to building robinhood:0x72d5bf142874d24d1565f8633621307fd2871111