与「comments」相关的搜索结果

Giving away 1 $BTC to a random person! As promised, I’m sending 1 BTC (~$69,162) to one lucky follower. Like, retweet and comment ‘BTC’ to enter. * If you’re not following, you will be disqualified. Winner announced in 24h! Comments will be locked after 24 hours, the winner will be announced. Good luck everyone!

BREAKING: Jensen Huang appeared “broken” in his final hours as Nvidia CEO, per Bloomberg. Nvidia’s board held an emergency meeting that ran late into the night after the latest affair reports, and by the end Huang had agreed to step down. The board left him no choice but to resign. According to people who spoke with him, his usual take-charge style was gone. He responded with indifference, saying things like “whatever” and “I don’t care,” and has since called himself a “piece of sh--.” He says he no longer cares what happens to him. His main concern is his wife and not “ruining the lives” of the women now linked to him. Inside Nvidia, employees are rallying behind him. More than 1,600 comments on internal forums call for his reinstatement, per Wired.

Want to get more out of ChatGPT and Claude? With @agentkeyapp , you can connect AI agents to external data sources and tools, helping you dig deeper, find relevant information and get more useful research result Watch and check comments to see how👇

Pelicans fans believe they found Dejounte Murray’s burner 😭 A YouTube account named “MadJay5” has been leaving lengthy comments defending Murray and calling out his teammates, including Herb Jones. Fans began suspecting the account belongs to Murray after noticing similarities between its writing style and Murray’s own tweets, including capitalizing the first letter of nearly every word. (h/t @PelicansDigest)

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!

Giving away 1 $BTC to a random person! As promised, I’m sending 1 BTC (~$73,943) to one lucky follower. Like, retweet and comment ‘BTC’ to enter. * If you’re not following, you will be disqualified. Winner announced in 24h! Comments will be locked after 24 hours, the winner will be announced. Good luck everyone!

She was 13, a straight-A student, when she sent her boyfriend one video. At her new school, a stranger sent her a link. It was on Pornhub, titled "13 year old brunette shows off for the camera." Too scared to tell her mom, she messaged Pornhub pretending to be her mother. Then it came back up. One copy hit 2.7 million views. In the video below, she tells it herself to the Canadian parliament. Wait for the 2.7 million views, and what the comments under that video said. Her mom was a strict Catholic, a single mother of six. Serena Fleites didn't want to bring this home. So she typed into Pornhub's own report form: "Hey, this is my daughter, she's only 14 now, this is child pornography, please take this down." They took a week or two to answer. Then another two weeks to actually remove it. She had been told Pornhub had a system. Once a video was flagged as child porn, it could never be uploaded again. "But of course that wasn't true, because a week after it's been taken down, it had been re-uploaded again." By then the video had gone around her school and the schools nearby. Strangers sent it to her. People threatened to send it to her family. She started ditching class, took drugs, dropped out and ended up homeless. "I ended up trying to kill myself many times. I ended up in mental hospitals." The copies kept collecting views. She had a hormone disorder: at 13 and 14 she looked 9 or 10. One upload sat at 2.7 million views under "hundreds of comments saying 'this is definitely child pornography, that girl can't be any more than 14, 13.'" Pornhub still wouldn't take it down. When they finally answered, she says, they hassled her for more details. A child had to prove she was the child in her own video. "I would have to go through the whole process of sending them pictures of me with my face next to my ID over and over and over again." Even then, every takedown dragged on, "which would gain hundreds of thousands more views." She told her family two days before the New York Times article came out. A 13-year-old flagged it. Hundreds of strangers flagged it. Pornhub asked for her ID. So was Pornhub just a slow website drowning in reports, or did it make money off every single week it made a child wait?