与「records」相关的搜索结果

I think the best case is to make the "monitor" as un-agentic as possible. We don't mind being "monitored" by various random tiny insects we don't even notice, even guard dogs are fine, but we really do mind if it's a globally connected networked system. And the intermediate case, human security guards with no recording equipment, we mind only a medium amount. The best idea I've come up with so far is to make these monitoring devices out of open-source verifiable hardware that has etched on it an open-weight LLM that classifies for a limited number of activities (basically, just violence; sorry, no scanning for jaywalking or not wearing a mask or drugs or unauthorized manufacturing or illegal immigrants, really just violence) and only records and forwards if that's what it sees. The device has no storage, no ability to load new algorithms, this is all it does. Also, a hash of every recording is published onchain (and a device can't record the next one until it sees confirmation of the previous one) so we can all count how much recording is done. Finally, everyone has a legal right to take any such device they see and grab it and dissassemble and verify the hardware themselves. Explicitly fund university clubs, hacker groups, etc to regularly do this.

🏀 FRIDAY'S FINAL SCORES 🏀 Franz Wagner records his 4th consecutive game of 30+ PTS, helping the @OrlandoMagic improve to 2-0 in @emirates NBA Cup Group Play! Desmond Bane: 21 PTS, 5 REB, 6 3PM, 2 STL

Multi-agent workflows have a scaling problem! The agents inside the same workflow rarely need the same amount of capacity at the same time. Say you have a planner, multiple research agents, and a final synthesis agent. The planner might finish quickly while requests start piling up behind one of the research agents. Scaling the entire application would add capacity everywhere, even though only one part of the workflow actually needs it. CanyonOS is an open-source, workflow-aware platform for multi-agent Python applications and the harness between your agents. Each agent runs as a separate service with its own queue and replica limits, so the busy research agent can get additional capacity while the planner and synthesis agents stay where they are. It also handles communication between the agents and gives you visibility into what happens across the workflow after a request comes in. CanyonOS records the path a request took, including the agents it called, parallel branches, model usage, execution time, and estimated model costs. And you don't need to add tracing decorators or a separate instrumentation SDK throughout your agent code. You still integrate the workflow with CanyonOS, but tracing is handled at the platform layer. I also ran a multi-agent portfolio analysis workflow through it with separate agents working across three stocks. A single request produced 10 traceable steps across the workflow, and I could see which agents ran, where the LLM calls happened, how long each stage took, and the estimated model cost. For multi-agent applications, being able to operate each agent independently while still seeing the complete execution path becomes much more useful as the workflow grows. CanyonOS is open source. Link to the GitHub repo in the comments!

Her name is Kimberly Powell. She is 48 this year and joined Nvidia in 2008. > November 8, 2026. Jensen Huang sends a letter to every Nvidia employee. > “I was unfaithful to my wife. My actions hurt her and our children. There is no excuse for what I did. I am deeply sorry.” > The affair was with Alice Huang, a Chinese businesswoman suspected by US intelligence of being a spy. > The board opens an investigation. > The FBI is involved. > Nvidia’s stock falls. > Then, three days later, the story gets worse. > November 11, 2026. The New York Times publishes a second report. > Jensen Huang had another affair. > A second woman. > A subordinate. > Someone who reports directly to him. > Her name is Kimberly Powell. > Vice president of healthcare at Nvidia. > Joined the company in 2008. > Promoted to senior director in 2016. > Vice president by the end of 2017. > Eighteen years at Nvidia. > One of Huang’s roughly sixty direct reports. > She is 48. He is 63. > Both are married. > March 2026. Nvidia’s GTC conference in San Jose. > Powell presents on AI and healthcare. > Her slides use animated images of Huang. > Then executives gather at a nearby hotel. > Huang and Powell are seen together. > Affectionate. Intimate. > A witness records it on their phone. > Huang’s security team spots the witness. > Escorts them away. > Asks them to sign a confidentiality agreement. > The video still exists. > Five former Nvidia employees confirm the relationship was discussed inside the company. > Nvidia’s code of conduct has a rule. > Personal relationships can create conflicts of interest. > The company says it promptly investigates reports of misconduct. > The CEO wrote the letter that begins the code. > He is now the subject of the investigation. > November 12, 2026. The board prepares to meet. > The Wall Street Journal reports the board could determine his future as soon as that day. > The board is preparing to oust the CEO who built the most valuable chip company on Earth. > Nvidia’s stock sinks more than 7% after hours. > Huang, Powell, and Nvidia have all declined to comment. > None of the allegations have been confirmed by any of them. > The first affair cost him his reputation. > The second affair may cost him his company. > He admitted one. He has said nothing about the other. > The board is meeting. > The investigation is expanding. > The man who kept his promise to Lori Mills is running out of promises to keep. He built the most powerful company in the history of computing. He admitted to one affair. Then a second woman’s name surfaced. The board is deciding whether he still runs the company he founded. His name is Jensen Huang. He is 63 years old. And for the first time in his life, the next move is not his to make.

🏀 WEDNESDAY'S FINAL SCORES 🏀 James Harden records his 345th career 30+ PT game, tying Allen Iverson for 11th most all-time as the @cavs pick up the win on the road! Donovan Mitchell: 23 PTS, 7 REB, 6 AST, 2 STL Jarrett Allen: 11 PTS, 14 REB

📊 @giyu_codes went looking for underserved industries buried in messy public records, pairing with Carbon to turn scattered public datasets into 14 interactive tools with live 3D visuals Explore all 14 builds in their thread ↓

Suiball Refund Announcement Thank you to everyone who supported us on this journey. We set out to build a secure hardware device that was more than just a hardware wallet: one fully native to Sui. We did it. Suiball went into manufacturing, and we were ready to ship the first batch to our supporters. After a wave of recent hardware wallet attacks across the industry, the Sui Foundation decided the risk of backing a hardware wallet project was too high right now. We understand that decision. Sui puts the security of its users and ecosystem first. Still, after years of intense development and a finished, working product, it's hard to say that we have to close Suiball down. That's the nature of building an ambitious startup. We had the right intentions and the right capabilities, but this one wasn't meant to be. How refunds work: 🔹 On-chain pre-orders (~80% of orders): You'll get your refund in USDC, airdropped straight to the wallet that holds your soul bound pre-order NFT. You don't need to do anything. This will happen within the next week. 🔹 Credit card pre-orders: You'll get an email asking for a Sui wallet address. Your refund will be airdropped there in USDC. We'll run a second airdrop once addresses come in. 🔒 All the personal information you gave us for device delivery, including your name, email, shipping address, and phone number, will be permanently deleted once refunds are complete. We won't keep any records. ⚠ We will never ask for your seed phrase, private key, or any payment. Only reply to emails from info@citadelwallet.io Suiball will officially close once all refunds are complete. Thank you for believing in us.

The Across domain is currently down while we secure it against an attack from earlier today. At ~18:45 UTC, a social engineering attack on @Namecheap (our domain registrar) gave a bad actor control of the Across domain. Within 15 minutes of this attack, we were alerted and immediately worked to shut the site down. SEAL911 marked across.(to) as a phishing site with major wallets, and Cloudflare worked with us to mark the domain as at risk, and later pulled the site’s DNS records. At the time of this post, Across.(to) is fully down, and the phishing site is no longer available. In the brief period before Cloudflare fully blocked the malware site, some users who visited across.(to) may have been affected. No third-party integrations or API users were affected. Users who believe they were affected should DM us with transaction details and revoke attacker permissions (see next tweet for details). Despite our best efforts, @Namecheap has been unresponsive, and we have not been able to properly secure the domain to bring Across’s services back up. Across’s frontend and API will remain down until we can properly secure them. We will always put user safety first. Across’s domain was fully locked down with best-in-class security practices; this unauthorized takeover should not have been possible. We will be investigating this deeply and will provide a post-mortem on how this domain takeover was possible once we have more information.