AI costs how much? GitHub Copilot users react to usage-based pricing
Ars Technica AI21h agoBusinessGitHub Copilot users are reacting to a new usage-based pricing system for AI features. Some report burning through their entire monthly AI credit allocation in a single day. The response highlights concerns about predictable costs and whether monthly allowances can support intensive AI-assisted development workflows.
Vercel Blob now supports OIDC authentication
Vercel Changelog1d agoReleaseVercel announced that Vercel Blob now supports OIDC authentication. The provided source does not include implementation details, setup instructions, supported identity providers, or migration guidance. Teams using Vercel Blob should review the official documentation before changing existing authentication flows.
GitHub Copilot’s new token-based billing spurs dev backlash★ 72
TechCrunch AI3d agoBusinessTechCrunch reports that GitHub Copilot will move to token-based billing on June 1, replacing a more predictable flat or request-based model. Some developers say their expected monthly costs could jump dramatically, citing examples from about $29 to nearly $750 or $50 to around $3,000. Others argue the worst cases may reflect heavy vibe-coding usage, while critics say Microsoft encouraged that behavior before changing the economics.
Cognition’s Scott Wu says AI coding agents shouldn’t replace humans
TechCrunch AI4d agoCommentaryCognition makes Devin, described by TechCrunch as the first and arguably most successful AI coding agent. Scott Wu says the product is not meant to supplant human programmers. The key takeaway is a positioning statement: AI coding agents are being framed as tools for software work, not as a direct removal of humans from development.
Run Docker containers inside Vercel Sandbox
Vercel Changelog4d agoReleaseVercel announced the ability to run Docker containers inside Vercel Sandbox. Because the original article text was not provided, confirmed details are limited to the title, source, URL, and publish time. The update is likely relevant to developers building isolated cloud workflows for containerized tests, AI agent execution, and sandboxed automation, but implementation limits and pricing require the official changelog.
markdown-svg-renderer
Simon Willison's Weblog4d agoNew ToolSimon Willison shared markdown-svg-renderer, a customized Markdown rendering tool with special handling for fenced SVG code blocks. It renders the SVG image and also provides a tab for switching back to the source code. Users can paste Markdown directly or load a CORS-enabled Markdown file or Gist by URL, with an example using LLM pelican logs for Opus 4.8.
How Conductor moved parallel coding agents from the laptop to the cloud with Vercel Sandbox
Vercel Changelog6d agoBusinessBased on the title, the article describes Conductor shifting parallel coding-agent execution from developers’ laptops to Vercel Sandbox in the cloud. The likely focus is cloud isolation, parallel agent workflows, and reducing dependence on local machine resources. The full article text was not provided, so implementation details, metrics, model choices, and concrete results cannot be confirmed.
Experimental native binaries for Vercel CLI
Vercel Changelog6d agoReleaseVercel’s changelog lists an update titled “Experimental native binaries for Vercel CLI.” The available source text does not provide implementation details, supported platforms, install commands, or performance claims. The main takeaway is that Vercel is experimenting with a native binary distribution path for its CLI, which could matter to developers who rely on Vercel CLI in local workflows or CI automation.
Uber president says AI spending is getting ‘harder to justify’
The Verge AI7d agoBusinessUber reportedly exhausted its annual AI budget just four months into 2026. President and COO Andrew Macdonald said the company is not seeing a clear link between increased Claude Code token consumption and more meaningful output. The story highlights a broader enterprise shift from AI adoption enthusiasm toward stricter scrutiny of cost, productivity, and ROI.
Vercel Domains now supports price sorting and availability filtering
Vercel Changelog7d agoReleaseVercel announced that Vercel Domains now supports sorting results by price and filtering by availability. The change appears focused on improving the domain search and purchase experience, helping users narrow candidate domains faster. No original body text was provided, so details such as sort direction, exact filter options, TLD coverage, or API availability should not be inferred.
Firecrawl joins the Vercel Marketplace
Vercel Changelog7d agoNew ToolVercel announced that Firecrawl has joined the Vercel Marketplace. Based only on the provided title, this appears to be a marketplace listing or ecosystem availability update. The title does not specify features, pricing, setup flow, usage limits, or integration depth, so teams should check the official listing before making adoption decisions.
Giving Agents Computers — Ivan Burazin, Daytona★ 75
Latent Space11d agoNew ToolDaytona 執行長 Ivan Burazin 分享該平台如何透過提供安全隔離的「開發環境沙盒」，解決 AI Agent 執行程式碼的安全與效能痛點。 公司目前取得驚人的 74% 月增長率，每日執行次數達 85 萬次，並推出專為 Agent 設計的全新「Agent Cloud」。 訪談深入探討了裸機沙盒（Bare Metal Sandboxes）的技術優勢、強化學習評估（RL Evals）以及 AI 時代下開發環境的演進。
Claude Code's product lead talks usage limits, transparency, and the "lean harness"★ 80
Ars Technica AI18d agoOpinionAnthropic 旗下熱門命令列 AI 助手 Claude Code 的產品主管 Cat Wu 近日接受專訪。她透露團隊在開發這款 Agent 工具時「沒有宏偉的藍圖」，而是採取刻意為之的靈活迭代策略。訪談重點圍繞在開發者最關心的 API 使用額度與成本限制、如何透過高透明度介面建立信任，以及如何利用「精簡測試架構（lean harness）」在不犧牲效能的前提下，優化 Agent 的執行效率與準確度。
[AINews] Codex Rises, Claude Meters Programmatic Usage★ 75
Latent Space19d agoCommentary本期 AINews 聚焦於 AI 寫程式 Agent 的長期發展趨勢。Anthropic 開始針對 Claude 的程式化使用（Programmatic Usage）進行計量與限制，這將直接影響開發者透過自動化腳本或第三方工具調用 Claude 的成本。另一方面，Codex 相關的自動化編程 Agent 影響力持續上升，顯示出 AI 在軟體開發流程中的滲透率正穩定增加。
How Superset built the IDE for AI agents on Vercel
Vercel Changelog23d agoCommentary本文介紹 Superset 如何在 Vercel 平台上構建專為 AI Agent 設計的整合開發環境 (IDE)。Superset 利用 Vercel AI SDK 簡化多模型對接，並透過 Next.js App Router 與 Serverless Functions 處理複雜的代理人工作流與工具調用。透過 Vercel 的全球邊緣網路，他們成功解決了 Agent 運作時的即時狀態同步與高延遲問題，為開發者提供流暢的協作體驗。
Custom tags available in beta on Vercel Sandbox
Vercel Changelog33d agoReleaseVercel 宣布在 Vercel Sandbox 中推出「自訂標籤（Custom Tags）」Beta 版功能。開發者現在可以為沙盒環境或實例加上自訂標籤，這將大幅提升資源管理、分類與監控的便利性。此功能特別適合需要頻繁使用沙盒進行 AI 程式碼執行、原型測試或多專案管理的開發團隊。
Query and visualize workflow data in Vercel Observability
Vercel Changelog56d agoReleaseVercel 宣布在其觀測性工具（Vercel Observability）中，新增對工作流（Workflow）數據的查詢與視覺化支援。開發者現在可以直接在控制台中追蹤多步驟工作流的執行狀態、步驟耗時與錯誤。這項更新大幅簡化了基於 Vercel Workflows 構建的非同步任務與 AI Agent 應用的除錯與效能優化流程。
Vercel is now available in Stripe Projects
Vercel Changelog75d agoReleaseVercel 宣佈與 Stripe Projects 達成整合。現在開發者可以直接在 Stripe 的專案管理介面中連結並管理其 Vercel 部署。這項更新旨在簡化同時使用 Vercel 進行前端託管與 Stripe 處理金流的開發流程，提升開發與營運效率。
Chat SDK adds Telegram adapter support
Vercel Changelog95d agoReleaseVercel 宣布為其 AI SDK 推出 Telegram 轉接器（Adapter）支援。開發者現在能直接將基於 Vercel AI SDK 建構的 AI 模型與代理無縫對接到 Telegram 平台，無需自行編寫複雜的 API 轉換與 Webhook 處理程式碼。這項更新大幅簡化了 Telegram AI 機器人的開發與部署流程，並能輕鬆實現串流回應。
New dashboard redesign is now the default
Vercel Changelog96d agoReleaseVercel 官方宣布，先前進行測試的全新儀表板（Dashboard）導覽設計，現已正式成為所有用戶的預設界面。這次重新設計旨在優化專案管理、部署流程與團隊協作的流暢度，提供更直觀、現代化的操作動線，幫助開發者更高效地管理多個專案與雲端資源。
Automatic build fix suggestions with Vercel Agent★ 75
Vercel Changelog105d agoNew ToolVercel 宣布推出內建 AI 助手「Vercel Agent」。當專案部署失敗時，該 Agent 會自動分析錯誤日誌，精確診斷問題並直接提供具體的程式碼或設定修復建議，大幅縮短開發者排查 CI/CD 錯誤的時間，提升部署效率。
Support for Sign in with Apple
Vercel Changelog112d agoReleaseVercel 宣布在其平台登入選項中新增支援「使用 Apple 登入 (Sign in with Apple)」。這項更新讓習慣 Apple 生態系的開發者能更快速、安全地存取 Vercel 帳密與專案，無須再手動輸入密碼或僅依賴 GitHub/GitLab 等第三方登入，並支援 Apple 的「隱藏電子郵件」隱私功能，提升了帳戶管理的彈性與安全性。
Simplified file retrieval from Vercel Sandbox environments
Vercel Changelog116d agoReleaseVercel 宣布簡化從其 Sandbox（沙盒）環境中檢索檔案的流程。過去在沙盒中運行程式碼或由 AI 生成檔案時，獲取這些檔案較為繁瑣；現在開發者可以更直觀、快速地提取沙盒內產生的檔案與資源。這項更新將顯著提升使用 Vercel 進行動態程式碼執行與 AI 應用開發時的除錯與整合效率。
Copy visual context to agents from Vercel Toolbar
Vercel Changelog119d agoReleaseVercel 宣布在 Vercel Toolbar 中新增「複製視覺上下文至 Agent」功能。開發者在預覽網頁時，可直接擷取當前視覺狀態與結構並貼給 AI 助理（如 v0）。這簡化了前端除錯與 UI 迭代流程，讓 AI 能更精準地理解並修正網頁視覺問題。
Claude Code Max via AI Gateway, available now for Claude Code★ 75
Vercel Changelog127d agoReleaseVercel 宣佈其 AI Gateway 正式支援 Anthropic 的終端機 AI 助手 Claude Code。開發者現在可以透過 Vercel 的網關基礎設施來運行與管理 Claude Code，此更新引入了「Claude Code Max」，提供更佳的請求監控、快取與額度管理功能，協助團隊優化 AI 開發成本。
Introducing skills, the open agent skills ecosystem★ 80
Vercel Changelog133d agoReleaseVercel 宣布推出「skills」，這是一個專為 AI Agent 設計的開放式技能生態系統。開發者可以透過此平台輕鬆定義、發布並重用各種 Agent 技能（如 API 呼叫、數據庫查詢等），並與 Vercel AI SDK 無縫整合。這項舉措旨在簡化 AI 代理的工具調用（Tool Calling）流程，建立一個標準化且社群驅動的 Agent 能力庫。
On-demand Vercel Agent code reviews
Vercel Changelog138d agoReleaseVercel 宣布推出「隨選 Vercel Agent 程式碼審查（On-demand Vercel Agent code reviews）」功能。開發者現在可以根據需求，在特定時刻主動觸發 Vercel 的 AI Agent 來審查程式碼，而不需要每次提交都自動執行。這項更新賦予開發團隊更高的控制權，能有效優化開發流程並節省 AI 運算資源。
Introducing bash-tool for filesystem-based context retrieval★ 75
Vercel Changelog146d agoNew ToolVercel 宣布推出 bash-tool，這是一項專為 AI 代理（Agents）設計的工具，旨在透過檔案系統進行上下文檢索。該工具允許 AI 執行安全的 Bash 指令（如讀取、搜尋檔案），從而更精確地理解專案結構與程式碼內容。這將大幅提升 AI 在進行程式碼生成、除錯及專案分析時的準確度與效率。
Chat with Vercel Marketplace integrations using Vercel Agent
Vercel Changelog166d agoReleaseVercel 宣布其 AI 助手 Vercel Agent 新增支援 Marketplace 整合服務。開發者現在可以直接在 Vercel 平台中，透過自然語言對話來管理、查詢或設定已安裝的第三方服務（如 Neon、Supabase、Upstash 等）。這項更新大幅簡化了跨平台配置的繁瑣流程，免去了在不同控制台之間來回切換的麻煩，顯著提升了現代 Web 開發工作流的整合度與效率。
Codex is Open Sourcing AI models★ 70
Hugging Face Blog173d agoReleaseHugging Face 釋出最新消息，指出 Codex 正在開源其 AI 模型。此舉結合了 Hugging Face 的開源生態與 Codex 在技能培訓（Skills Training）領域的專長，旨在為全球開發者、學生及研究人員提供更具可及性的 AI 工具，進一步推動 AI 實作技能的普及與教育發展。