Future AGI 1.47.0 新增通话指标并改进 AI 智能体回答评估
Future AGI 1.47.0 发布，在运行分析中新增通话与语音指标卡片，并修复模拟通话结果与运行详情的对齐问题。评估对话时，错误语言回答、涉及其他产品的回答以及未获回复的请求现统一计为未处理请求；测试环境评估还修复了完整提示词和对话参与者标识的传递。聊天构建器页面支持折叠与调整宽度，宽度在窗口缩放后保留。
Awaiting translation
#Testing/verification
#Testing/verification
0 items todayTproger · ПрограммированиеAI score1212
Tproger · ПрограммированиеAI score1515 Future AGI 1.46.0 为模拟分析加入决策优先级
Future AGI 发布 1.46.0，核心改动在 Simulate 模块，为分析多次运行结果引入决策优先级，Runs 标签页现按环境中完整运行次数显示徽章。该版本还优化了运行摘要生成，以及 API v3 搜索场景时的任务处理，适合运行次数较多的团队。项目支持自行部署，云版本可免费开始使用。
Awaiting translation
青稞AIAI score2929 V-Rubrics 用 35 万条细粒度准则细化多模态强化学习奖励
南洋理工大学 S-Lab、A*STAR 和 UIUC 团队提出 V-Rubrics，将 50,248 个视觉样本拆成 352,938 条可逐项检查的准则，让视觉事实、推理步骤和任务要求分别参与奖励计算。
Awaiting translation
InfoQ · AI CodingAI score7171 Cloudflare 推出 Worker Previews，为每个 Git 分支提供隔离预览环境
Cloudflare 发布 Worker Previews，让每个 Git 分支拥有独立且接近生产的环境，各自有稳定 URL、独立配置和状态，并带独立可观测性。
Awaiting translation
Cursor · ChangelogSelectedAI score6262 Cursor Launches Two Bots: Rollouts and Security Review
Cursor has released two bots, Rollouts and Security Review, both available on Team and Enterprise plans.
Why it matters: The official docs cover the monitoring and security review workflows for both bots, so readers can judge whether they fit into their existing delivery pipeline.
Lovable · BlogSelectedAI score6060 Lovable Ships Opus 5.5: Faster Builds, Quality on Par with Opus 5
Lovable has shipped Opus 5.5, which the company says matches Opus 5 in results while cutting the number of steps by one-third to one-half. On Lovable's internal benchmarks, Opus 5.5 ties Opus 5 on 0-to-1 builds and iterative code changes, and comes out 4% to 6% ahead on validation discipline; across all reasoning effort levels, steps per task drop by 26% to 57% and input tokens fall by 21% to 59%, with the differences significant at the 95% confidence level.
Why it matters: Lovable shares official comparison data between Opus 5.5 and Opus 5 on step counts and tokens, so readers can judge the real change in build efficiency.
OpenAI Developer Blog · CodexSelectedAI score6565 OpenAI Releases Daybreak and Codex Security, a Security Workflow
OpenAI has launched Daybreak, combining ChatGPT, Codex Security, and the open-source Codex Security CLI into a security defense workflow that covers pre-merge PR reviews, repository and vulnerability backlog scans, and regular CI checks.
Why it matters: The official documentation walks through the full Codex Security workflow—from PR reviews and repository scans to CLI-based batch scanning—so you can decide how to plug it into your existing security processes.
Simon Willison · Coding AgentsAI score6060 用 Bun 1.4 的 Bun.WebView 实现 shot-scraper 风格的 JSON API
Simon Willison 用 Claude Code for web 做了一个约 150 行、零依赖的 TypeScript 服务原型，基于 Bun 1.4 实验性的 Bun.WebView 提供 shot-scraper 风格的 JSON API，支持执行 JavaScript 和输出 PNG/JPEG/WebP 截图，无需 Puppeteer 或 Playwright。
Awaiting translation
Jesse VincentSelectedAI score7878 Superpowers 6 发布：构建提速最高 50%、token 花费降低最高 60%
Superpowers 6 发布，作者称在 Anthropic 评测基准上构建耗时降低 50%、token 花费降低 60%，主要来自合并规范符合性与代码质量两个评审 agent、预先生成评审用的 diff 包让评审者少跑 git，以及调整编排器对任务所需 agent 类型的指引。
Awaiting translation
Why it matters: 作者用自建评测套件量化了 Superpowers 6 在构建耗时和 token 花费上的改进，并公开了实验记录与失败结论。