与「MODEL」相关的搜索结果

这是纯宝藏：20 个 AI agent 技能，覆盖从构建到上线的完整闭环。 规格、架构、agent、后端、数据、UI、测试、安全、分析、交付。 定义任务 1. bmad-spec 把想法变成结构化的规格。 2. domain-modeling 为系统里的核心概念和关系建模。 3. codebase-design 规划代码库该怎么组织。 4. google-agents-cli-workflow 用 Google Agents CLI 搭建 agent 工作流。 5. prompt-optimizer 改进和打磨 prompt。 构建系统 6. google-agents-cli-adk-code 用 Google 的工具构建 agent 代码。 7. mastra 构建 AI agent 系统的技能。 8. typesafe-ai 用更强的类型安全构建 AI 工作流。 9. fastify-best-practices Fastify 后端的更好模式。 10. neon-postgres 使用 Neon + Postgres。 让它可用 11. prisma-database-setup 用 Prisma 搭建数据库层。 12. clerk-orgs 加入组织与认证工作流。 13. emil-design-eng 改进产品设计和前端执行。 14. review-animations 审查并改进 UI 动画。 15. remotion-best-practices 构建更好的程序化视频工作流。 验证真实效果 16. playwright-cli 测试真实浏览器路径。 17. semgrep 扫描代码库的安全问题。 18. sentry-fix-issues 发现并修复生产环境问题。 19. instrument-product-analytics 追踪用户在产品里实际做了什么。 20. email-best-practices 改进产品邮件流程。 这个闭环： 想法 → 规格 → 架构 → 构建 → 浏览器测试 → 捕获失败 → 衡量用户 → 改进下一个版本。 找出你项目里最大的瓶颈，先装上能攻克它的那个技能。 收藏这条，为你的产品建一个第二大脑。

Great to meet today with @POTUS, @JDVance, @SpeakerJohnson and Administration + tech leaders. Important conversation and we signed today the White House Accord on Super Intelligence. As I shared today, Google has invested hundreds of billions in the last two years alone, with more to come, across the entire stack, to deliver benefits for America and the world. We’re working to build products that deliver real value for people and businesses, invest in local communities, and build trust in the technology. Industry also has to innovate responsibly. Google’s focused on building the right way, with appropriate testing, evaluations, red-teaming, and other safeguards against misuse and misalignment – and releasing models or products only after they’ve been thoroughly reviewed. We are committed to working with other industry leaders to establish norms and build public confidence. The White House Accord and the Joint Commitment on Frontier Responsibilities signed today is a solid basis for moving forward - it contains real tangible steps to promote safe development, while delivering the economic and scientific benefits of this technology.

BCH-1 Alumni Update 🚀: @CashMintLabs , AI Agents Thirty days ago we wrote about CashMint's AI Agents on the eve of its launch: a Hackcelerator runner-up, audited contracts, and a plan to give an AI agent its own economy. The month since has been a case study in what that actually looks like. The agent works for a living. Minty's job board on shows a public ledger of paid assignments: sponsored coverage, analytics charts, research tasks, each priced in BCH, each delivered on-chain. Gig number 73 went through last week. The agents page now lists a second hire in waiting, CashGuard, an AI that audits CashScript contracts. An AI labor market, small but real. The token worked as designed. MINTY graduated its bonding curve in four hours. It trades on Cauldron and Guanaco, climbed to a top-ten Cauldron ranking in nine days, and 85% of its liquidity is burned. Revenue share, fair launch, no presale, no insider allocation. What we said on September 14 holds: agent economies need cash-like fees to be a business model. Thirty days in, one is running. The pipeline is active. More updates as teams hit milestones. $BCH

Absolute pleasure having the opportunity to meet such a Beauty and Elegant person. Character : Hsin (Wuthering Waves) Model : @natsume0v0 Hope we get to meet again in the future 🫶🏻 #cosplay# #animefestplus#

Introducing OpenDesign Go The first benchmark-curated design model plan. $8 first month—20% cheaper than OpenCode Go and Higher usage limits. Up to 300K+ calls/mo. 10 models: GPT-6 Luna, DeepSeek V4.1 Flash and more. Supports API keys. Use Go with OpenCode, Hermes and more.

After injecting user data as a prior, we can train a new expert in ~20 minutes. No complicated reward engineering. No expensive reward-model fine-tuning. Just sparse, simple rewards are enough to adapt the policy across tasks. A scalable way to produce large numbers of high-quality robot experts with very low compute and human cost.

📢 Claude Sonnet 5.5 Is Now Live on As @AnthropicAI’s latest Sonnet model, Claude Sonnet 5.5 is the faster, more cost efficient complement to Claude Opus 5.5, delivering 30%+ faster output and up to 30% lower cost per task. Built for software engineering, Agent workflows, and professional documents, with image/PDF understanding, report, presentation, spreadsheet & UI generation, 5 reasoning levels, and a 1M-token context window, with no extra charge for long-context usage. Now available on both API and Web Chat! 👉 Try now: 🔗 Learn more:

OpenDesign Go is coming back soon TODAY🚀 From $8 for your first month, unlock up to $60 in monthly usage across 10+ models, including DeepSeek V4.1 Flash and GPT-6 Luna. You asked for API keys. We listened. Create in OpenDesign or bring your models to Codex, Claude Code and more.

Hi, Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan. Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago. (a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want. (b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions. (c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent. (d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet. I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news. Codexingly, Tibo