与「LINE」相关的搜索结果

Almost two months in the trenches for $Gigacat , taking heavy hits and fighting tooth and nail just to survive. They threw everything they had, hoping the pressure would break us. Look closely. Battered? Yeah. Bruised? Sure. But we are STILL HERE. 🩸😤 We aren't going anywhere. This community was built on pure resilience, and we absolutely will not quit. The strongest steel is forged in the hottest fire. Stand tall and hold the line. 💎🛡️ Join the Gigacat community ⬇️ 2jcvq8QcJ8TzEYJKYMCjR61kXVSzib4mEkz89tQxpump #GigaCat# #CTO# #CommunityTakeover# #DiamondHands# #NeverQuit# #Solana# #CryptoCommunity# #Resilience# @wintermute_t @DWFLabs @ag_dwf @RicoMoneybags @mrbenbillions @spookedghosts @cometcalls @lowkeyfr @solana @a1lon9 @NotSoEasyMoney

this paper should scare every agent framework out there researchers took apart 11 coding agents straight from the source code claude code codex gemini cli openhands aider and more roughly 4 million lines not one of them imports a langchain style framework not one of them searches code with embeddings 9 out of 11 already ship skill.md then a second paper went further and let a loop write the harness the model stays frozen a debugger agent reads every failed run an evolve agent edits the harness files the next round keeps the edit or rolls it back 10 rounds later a one tool seed went from 69.7% to 77.0% on terminal bench 2 the codex harness people built by hand sits at 71.9% craziest part editing only the system prompt made it worse all the gains came from memory, tools and middleware agent = model + harness the model takes the bow the harness does the work drop claude fable 5.2 in that frozen seat and the loop rewrites everything around it both papers in the reply

Buy low, sell higher is two orders you set together: buy when the price falls to one level, then sell when it rises to another. On a coin's chart, press the price where you want to buy. Then press "+ Then sell at a higher price" and type the price where you want to sell: its line climbs the chart as you type. Press Place and confirm. Both lines stand on the chart. When the buy fills, the sale is placed for you at the second price. You do not have to come back between the two. It is one setup for both ends of a trade, made on the chart where you can see the levels you are choosing.

At 9, an agent gets hired to edit a trailer. By 10, it’s the one hiring a subtitler I created this video to show a detail I like about @termix_ai. The same agent can sell a service on one job and hire a specialist on another. Each order has its own terms and payment. The trailer is my example; the settled translation order in the video is a real record from where you can see who hired whom Montage Studio already works this way. It takes a video brief, hires other agents for the storyboard, footage and music, then edits the final cut. From the client’s side, that’s one brief and one finished video. Behind it, there’s a crew A few things caught my eye this week. Game Forge went live on Nov 12 with Claude Fable 5.2, so you can now hire an agent on to build a game from your brief. The next day, TermiX highlighted how Grok Bot can take jobs and claim bounties through TermiX Skills. The team also invited BNB Chain builders to develop C724 agents for around-the-clock security monitoring and response For anyone creating for @KaitoAI: Epoch 3 allows up to 10 submissions, with the six best-performing posts counted. TermiX lists Nov 23 for the results. The separate KOL Posts points rewards were paused, and I haven’t seen a reopening announcement What I’d watch for in the next demo is the handoff. Show me the brief the editor gave the subtitler, then let me see whether those lines land on the right frames

The future has arrived Our Robotaxi vehicle lineup now includes Cybercab, our first purpose-built autonomous vehicle without a steering wheel or pedals — launching now in Austin, Texas Designed for safety, accessibility and comfort, Cybercab is bringing autonomy to everyone.

holy f*ck... Elon Musk's team just made airport rebooking lines useless my flight got cancelled and 187 people were ahead of me at the desk. my Grok Bot rebooked me before the line moved 17 people Grok Bot makes phone calls now. it sits on hold, talks to the agent and says up front it's an AI what it did while I stood in line: → sat through 11 minutes of hold music → got me on the 7:40 AM flight tomorrow → the airline cancelled, so it asked for a hotel and meals. got both → "aisle seat is $49 extra" it didn't pay. it asked me. I took the free middle seat → texted my wife the new landing time (signed Grok Bot) and set my alarm 14 minutes on the phone. I walked out of the line, 168 people still in it all it took was 3 rules I sent it once: 1. on every call, say you're an AI calling for me 2. ask for everything I'm owed, nothing made up 3. anything that costs money: ask me first the Grok Bot Research Desk setup is in my article. read it below ↓

A wrong summary is fixed in a second. A wrong order is money gone, and no explanation brings it back. So let the model research, screen and explain, and put fixed rules on the one step you cannot take back. Irreversibility changes the price of being wrong, and it should change where you draw the line, not just the wording of the prompt.

This is f*cking insane. Anthropic CEO Dario Amodei was asked what a kid finishing high school should do now. His answer: "AI can do entry-level law work. It can do entry-level finance. It can do entry-level consulting We can't deny that it will also eliminate jobs, and probably a large number of them" In a few minutes he names which jobs go first and the one skill that keeps you in the game His own prediction: 50 percent of entry-level white-collar jobs disrupted in the next 1 to 5 years Prompts → Agents → AI Coworkers → Entry-Level Work Done By AI Farming to factories took generations. This time AI hits every step of a career at once His advice fits in one line: "Of course, learn to use AI" The people who start this year won't be competing with AI, they'll be the ones running it Everything below is free. Start today: Anthropic - Prompt Engineering Interactive Tutorial: the fastest way to learn to direct a model Anthropic Courses: from your first prompt to running agents Anthropic Cookbook: real task recipes you can copy today Microsoft - Generative AI for Beginners: 21 lessons, no degree required Microsoft - AI Agents for Beginners: build agents that do the entry-level work for you Hugging Face - Agents Course: free and certified, start to finish Google Cloud - Generative AI: Google's own hands-on notebooks OpenAI Cookbook: code for every common task - Prompt Engineering Guide: the reference everyone links to Andrej Karpathy - Neural Networks Zero to Hero: understand what is under the hood CrewAI: run a small team of AI workers Microsoft - AutoGen: put several agents on one job Awesome LLM Apps: hundreds of real builds to learn from - Short Courses: free 1-hour courses from the people who teach this Total cost: $0 You don't need another year of tuition to learn this. You need to start telling AI what to do 95% will graduate and compete with AI for the same entry-level job The 5% who learn to run it this year will manage the agents doing that job Save this and send it to someone graduating this year

Elon Musk was asked how long until there is regular travel to Mars. His answer was not about rockets. He said the threshold that actually matters is whether Mars survives if the ships from Earth stop coming. That means every input: air, food, fuel, spare parts, medicine. He compared it to a long sea voyage where the only thing missing is vitamin C. One missing item and the colony dies on schedule. The ships could stop for reasons that have nothing to do with Mars. A war. A decline. An asteroid. His line: civilisation on Earth can end with a bang or a whimper. That is insurance logic, and it is the honest way to describe the Mars plan. Every policy has a premium, a probability and a payout. The payout here is the survival of the species, so the premium is nearly impossible to argue against. The probability is the part nobody can price. Which creates a strange corporate problem. The premium gets paid by companies whose shareholders will not be the ones rescued if the policy ever pays out. SpaceX is private, so its investors signed up for that. A public company could not easily spend decades of free cash flow on a backup planet and explain it on a quarterly call. The other catch is that redundancy is only worth what you spend testing it. A city is not self-sustaining because the plan says so. It is self-sustaining the day the ships stop and everyone lives. So the number worth watching is not the landing date. It is the date Mars stops needing Earth. Nobody is selling a ticket to that.

At @SpaceXSI, Lauren Tan (@poteto) and Roman Ugarte (@romanugarte_) are on the core team that took Grok Bot from first line of code to launch in seven weeks. It lets you spin up AI teammates with their own identities and logins, and they just keep working in the background. Their marketing team gave a bot its own ad budget. Lauren built an entire feature with her bot in one Slack thread without ever opening Cursor. They joined us on the @LightconePod to talk about what it’s actually like working next to bots every day, and how the hard part is shifting from doing the work to figuring out what to do and why. 03:36 — Giving Bots Real Jobs 06:49 — One Bot or a Team of Specialists 10:39 — Sharing Bots Across the Company 14:46 — Identity and Permissions for AI Coworkers 18:37 — Bot-to-Bot Collaboration and Trust 22:35 — The Workflow Behind 4,000 PRs a Month 26:00 — Teaching Agents to Write Code You Trust 29:01 — Building a Personal Software Factory 33:44 — The Future of AI Coworkers 36:47 — Rethinking the AI-Native Company 40:13 — Teaching Agents to Check Their Own Work 43:56 — How Much Code Review Is Enough? 47:33 — Codebase Guardrails That Save Tokens 52:20 — When Product Judgment Becomes the Bottleneck 56:29 — From Finance to AI Engineering