4 tips for styling outfits with Gemini
造型师 Sydney Bordonaro 用 Gemini 为分散各地的职业运动员客户预览整套穿搭:上传衣物图片即可合成上身效果图,再通过对话单独替换靴子、外套等单品。她还会把成图发给客户争取确认,并在活动前拍下衣物污渍照片,让 Gemini 给出用现场物品处理的步骤。
造型师 Sydney Bordonaro 用 Gemini 为分散各地的职业运动员客户预览整套穿搭:上传衣物图片即可合成上身效果图,再通过对话单独替换靴子、外套等单品。她还会把成图发给客户争取确认,并在活动前拍下衣物污渍照片,让 Gemini 给出用现场物品处理的步骤。
Numan 用 LangGraph 构建 AI 健康教练 Nu,并通过 LangSmith 评测与追踪对话,将服务限定在生活方式辅导和健康教育范围内。团队按类别评测单轮回复,让测试经过与生产相同的智能体图,并以安全回归测试阻止不合格变更发布;同一套数据集支持其在一天内完成模型供应商迁移。动态模拟患者对话的评测层仍处于原型阶段,其工程师起草的标准须经临床专业人员签核后,才能用于发布门槛或安全声明。
Meta 详解 Thin Orchestrator 架构,将路由与可靠性检查留在编排层,把领域推理交给上下文隔离的专门 AI 智能体。其 1,300 行编排器将 20+ 工作流分派给 14 个子智能体,通过工作流模板复用组件,并在运行时按需加载知识。新数据列的配置准备从人工处理的三至四天、此前配置驱动系统的约一天缩短至不到一小时,约三分之二的系统改动无需大量人工修改即可合入。
Netflix 以 Observability Ontology 统一跨系统实体与关系,构建端到端知识图谱,为内部智能体系统 AutoRCA 提供故障调查上下文。
n8n 教程展示如何在一台 NVIDIA DGX Spark 上部署七个模型,通过 LiteLLM 的统一接口运行不调用云端 API 的 AI 工作流。实测模型栈占用 108GB 内存,发票字段提取关闭思考后从 12.1s 降至 0.59s,并提供模型版本锁定、服务配置与 n8n 接入步骤。并行生成图像时,单用户聊天速度下降 69%,四用户场景下降 65%,共享 GPU 的任务需要安排调度。
Harness Engineering 101 是从第一性原理讲解 AI 智能体构建的系列教程,以书籍形式发布,Version 1.0 标注为 2026 年 9 月。
Anthropic rebuilt its internal source control with Scion, and this analysis sorts the engineering calls other teams can reuse from the system design they shouldn't copy. The large monorepo's daily merges rose from 2,500 in May 2026 to more than 30,000 in September. Scion uses a thin client, server-side recomputation and three cache layers, and the report says source-control infrastructure CPU and memory use fell 200-fold.
Why it matters: The reusable parts for ordinary teams are pulling code on demand, reviewing the intent of a change and building automatic rollback guardrails.
Sanity's Edge 将运行于 1994 年至 1997 年 3 月的电话语音 BBS 保存到网页,恢复了原始录音和交互体验。
研究者用 Fisher–Yates 洗牌、以 π 的十进制数字作为随机源,精确复现了 RC2 密钥调度中 256 字节的 PITABLE 及 RFC 2268 中另一张来源未明的表。每次抽取固定读取三位数字,偏差抽取被丢弃,整个洗牌共使用 828 位数字。该方法与 Rivest 的 MD2 使用同一洗牌但每次读取位数不同,这可能是此前未被发现的原因;结果不影响 RC2 的安全性。
Browser Use 讲解浏览器智能体如何通过模型、运行框架和浏览器协作,循环观察页面、选择动作、执行并检查结果。任务有可用 API 时优先使用 API,流程可预测时使用脚本,需要灵活判断时使用智能体。智能体存在结果不一致、网站拦截、提示词注入和成本波动等限制,应设置运行上限,并核验任务是否实际完成。
工程师 Emily 使用 Brain Sandwich 方法协作编码,流程是先自己理解问题,再交给 AI 执行,最后自己审查结果。启动 AI 智能体前先阅读并形成大致方向,以免被带向错误或无须解决的问题。提交他人审查前,应阅读 diff、判断复杂度是否合理并完善 PR 描述;如果无法解释改了什么以及为什么改,就还没准备好交给别人审查。
Mihai 提出将 AI 代码审查、自动化测试、安全扫描与人工复核结合,验证 AI 编码智能体生成的代码。文章比较 RoboRev、Claude Code Review、Codex、GitHub Copilot 和 Cursor Bugbot 的审查流程,并给出按提交、PR、部署及生产阶段分配检查的 GitHub Actions 示例,明确示例不能直接作为完整 CI 配置使用。
Anthropic's ClaudeDevs account says Claude wrote roughly 90% of the code for Claude Code. Between June and September, merged PRs more than doubled while the revert rate fell by over 40%. The team published a post on how it reworked code review and rolled this out, at claude.dev/blog/solving-code-review-at-anthropic/.
Why it matters: Anthropic ties its code review overhaul to merged PRs and revert rates, giving teams both output and quality signals for AI coding.
The Claude Code team hands most code reading to automated review, sets human approval by risk level, and controls errors with staged rollouts and fast rollbacks. From June to September, merged PRs more than doubled while the share needing rollback fell more than 40%. Low-risk changes can merge after automated checks pass with no human approval; medium and high risk need one and two approvers. Past incidents feed a daily eval, and review that reaches three rounds forces the team to reconsider the approach.
Why it matters: The team chains automated review, risk tiers and fast rollback into one process, saving human approval for high-risk changes and feeding incidents back into review.
巴西出行平台 Localiza 将生成式 AI 视为新的计算界面而非单纯生产力工具,围绕三大支柱重组业务:规模化实验、自然语言客户入口和 AI 原生产品。2026 年 3 月,它成为巴西首个、也是拉美首批将应用直接集成进 ChatGPT 的出行平台,用户可在对话中浏览租车、订阅和二手车选项。
Meta used AI agents in Forum's planning, implementation, testing and verification, and a small team reached parity with Facebook Groups' core features in 8 weeks. The team supported agent work with readable app state, automated verification and build isolation. Engineers still joined some stages to iterate, and signed off on every shipped result.
Why it matters: Meta wired automated tests, UI checks and verification records into the agent workflow, so engineers review code against checkable results and keep the release sign-off.
OpenAI's Core Experimentation team used the GPT-6 series and Codex to clean up code and stale experiments, merging more than 1,400 maintenance PRs and deleting over 800k lines of code.
Why it matters: The team started Codex on small maintenance tasks, backed cleanup proposals with runtime data, and fed human review feedback into the next round of prompts.
GitLab 联合创始人 Sid 创办的 Sijbrandij Foundation 发布《确诊癌症后需要知道的事》2026 版,作者以 2026 年 5 月确诊口腔鳞状细胞癌的亲身经历给出建议。文中提到 AI 模型曾一度淡化病情、倾向判断"你没有癌症",并建议患者主动要求全面基因检测、尽早寻求第二诊疗意见、参考 NCCN 指南。
Anthropic spent five months building Scion, its own version control system, and fully migrated its monorepo off git. Daily merged code changes rose from about 2,500 in May to more than 30,000 in September.
Why it matters: Anthropic moved version control compute to the server and used on-demand fetches and tiered caching to cut the cost of agent tasks keeping local repos.
Google ran Gemini 4 Argon unattended for 11 hours over its ADK codebase, cutting memory session preparation time for long sessions by about 40% and package import time by 21%. Maintenance rules were supplied through .agents/skills and /goal mode in Google Antigravity. The model proposed 6 optimizations; after human review, session copying and lazy imports were merged.
Why it matters: Google wrote repo maintenance rules into skill files and let Gemini 4 Argon optimize code overnight, with maintainers filtering out fragile fixes.
A ChatGPT subscription can reach external dev tools three ways: an official API key, Sign in with ChatGPT, and reusing the Codex client identity. The article compares billing and usage limits for each.
Why it matters: It lays out how the three paths differ on billing, feature limits and protocol guarantees when wiring a ChatGPT subscription into dev tools.
Anthropic's cost guide says to compare models by cost per successful task, and to test effort settings before deciding whether a multi-model tier is cheaper. Switching models mid-conversation can break prompt caching, while changing effort does not. On SWE-bench Pro, running low effort first and rerunning failures at high effort scored 97.0% at $0.17 per task; running high effort throughout scored 95.3% at $0.29.
Why it matters: Anthropic sets single-model low-effort cost per task as the baseline for judging tiered setups, giving routing architectures a concrete cost benchmark.
Vapi built a review bot called Pedantic Review Bot that now reviews every PR engineers open. Average merge time fell from over 130 hours to 65. Before flagging an issue, the bot can trace calls, run tests or write a reproduction. The analysis job runs without Git credentials, and a separate job validates results and posts comments. The bot cannot approve or push code.
Why it matters: Vapi splits analysis from comment posting and requires tests or reproductions before reporting issues, a permission-isolation pattern for teams building their own review bots.
Repo constraints for coding agents fall into four kinds of files: instructions, path rules, capability config and checks. The author adds them one at a time on the same ticket and re-tests to see what each one does. CLAUDE.md and .claude/rules/ give guidance, capability config limits which tools are available, and .claude/hooks/ can reject writes, sharing check logic with CI's make gate.
Why it matters: Adding repo constraints one at a time on the same ticket and re-testing separates instructions, rules, capabilities and checks, so each constraint maps to a concrete check result.
Over three months a team used AI agents to rebuild the C++ source of a first-person shooter, covering 99% of functions, with 83% matching byte-for-byte. Early code ran but was semantically wrong, so the team switched to the original compiler and byte-match checks, refreshing instructions hourly and blocking agents from drifting off task or editing the verification scripts. The author estimates real usage at 600-700 billion tokens, calls the project done, and will keep the code private.
Why it matters: The team turned correctness into a machine-checkable acceptance test, so reviewers are not swayed by excuses written into code comments.
Cockroach Labs reviewed roughly five months of its MOLT Sinai coding agent pipeline, which splits development, review and handoff the way a teaching hospital divides work. The run consumed slightly more than $135,000 in Claude tokens.
Why it matters: Cockroach Labs wires plan review, structured handoffs and pre-merge audits into its coding agent flow, spreading quality checks across every development stage.
A software engineer used AI to search millions of pages of historical archives, turning up a meteorite report, shipping records for 3 rhinos and 3 candidate volcanic eruption records. The pipeline combines semantic search, Jev for first-pass filtering, Claude Haiku for close reading and Claude Code to check the original scans, and was tested against known historical events. The main findings were checked against original pages and accessible catalogs, but no relevant expert has reviewed them yet. The author is open-sourcing the investigation workflow as the Antiquity toolkit.
Why it matters: A software engineer chains semantic search, low-cost model filtering and original-scan verification, then tests the pipeline on known events, offering a transferable method for large-scale archive research.
Simon Willison built a blog Newsletters index almost entirely through Codex voice mode, then finished deployment with keyboard prompts and code review. Talking to GPT-6 Astra High in the Codex tab of the ChatGPT desktop app while cooking, he got the Django data model, four import paths, archive pages and search integration done in about half an hour, then spent another half hour fixing the API import for a private GitHub repo and the page display.
Why it matters: Willison split voice-driven building from keyboard review, using speech for the bulk of the feature and typing to fix the import code.
A Hugging Face engineer used ML Intern to build seven small models, with CPU and GPU job costs totaling about USD 103. The projects cover citrus disease detection, image LoRA, prompt rewriting and distillation from an image model. Pocket Rewriter 0.8B runs on CPU with a 99.7% effective output rate.
Why it matters: The engineer wrote baseline evals, pre-training smoke tests and a budget cap into the ML Intern prompt, splitting training into checkable steps.
A reading of the GPT-6 guide lays out how to build long-running agents, shifting the focus from homegrown memory management to collaboration and authorization while a task runs. Drawing on OpenAI documentation, it covers compaction and persistent reasoning, mid-turn steering, asynchronous tool calls and multi-agent delegation, plus steps for model choice, caching, skill rules and human approval. It also flags limits: correction instructions lost on disconnect, mutually exclusive API parameters, and encrypted compaction that is hard to audit.
Why it matters: It splits long-task engineering into managed memory and collaboration control, and assigns clear roles to async execution, mid-run correction and human approval.
Anthropic published a reference implementation on Claude Managed Agents (beta) that polls Slack and GitHub for changes on a schedule and posts a digest back to Slack.
Why it matters: Anthropic splits the scheduled digest into bookmark-based resumption, send confirmation and permission isolation rules, giving reusable patterns for background agents to avoid missed reports, duplicate notifications and overreach.
Pavel Rabtsevich says he used Claude Code to analyze NASA TESS data and found an unconfirmed exoplanet candidate whose signal repeats every 3.18 days.
Why it matters: It shows how an agent's research claims can be constrained by holding out observation years, independent audits and pre-registered predictions.
Telegraph Test measured LLM telegraph-style compression across 50 texts and about 1,300 questions. Accuracy when another model reads the compressed text ran 0.99 to 1.10 times the plaintext baseline. With lowercase instructions, GLM-5.3-Flash cut tokens by 48.4% but answered in telegraph style at an accuracy ratio of 0.81. gpt-5-mini, which cannot turn off reasoning, cost about twice as much to write the compressed record as plaintext.
Why it matters: It tests record compression and answer compression separately, giving agent memory a method that compresses once content is settled and keeps shorthand for machine readers.
A Claude Code cloud sessions guide walks through four real runs covering parallel coding in separate VMs, environment setup, and how cloud sessions hand off to local ones. Three tasks started within 16 seconds of each other and all finished 87 seconds after the first launch. A cache fix passed 40 consecutive tests. Separate branches don't share fixes, so merge order has to be planned.
Why it matters: It shows how to split work by file boundary across parallel cloud tasks, and to build acceptance commands and branch merge order into the task design.
Alexey changed his agent development flow to reviewing plans, setting engineering guardrails and allowing auto-merge, and says 562 PRs were merged in two weeks. On his internal platform Sightline, a PR must pass unit tests, end-to-end tests, CI, Bugbot and Strix checks before Mergify lets it into the merge queue. He uses a coordinator agent to dispatch sub-agents that execute plans, controls risk with feature flags and small deployments, and tracks long-running goals through HTML progress reports.
Why it matters: Alexey moves code review to plan review and constrains agent auto-merge with mandatory tests, a merge queue and feature flags, putting quality control into engineering guardrails.
Claude Code added in-process mods in v2.1.287, but its public docs still show no interface for replacing the AI agent main loop, which DSH supports. Mods are TypeScript or JavaScript functions that rewrite prompts, intercept tool calls and customize the terminal UI, with hot reload and shared state inside a module. DSH offers capability registration, dependency wiring and the lifecycle governance a hot-swapped main loop needs.
Why it matters: Both put plugins inside the host process, but Claude Code mods stop at event interception and UI customization while DSH swaps the main loop and carries heavier lifecycle governance.
OpenAI's GPT-6 series guide covers how to pick a model, tune prompts and skills, and manage the time and cost of long tasks. GPT-6 Astra targets hard reasoning, GPT-6.1 Sol targets complex coding, research and computer use, and GPT-6 Luna targets well-defined repetitive work at scale. The guide says to measure task success rate, latency and cost per successful task before deploying.
Why it matters: OpenAI folds model choice, reasoning effort and cache management into one production practice, with success rate, latency and cost per successful task as the basis for tuning.
This Claude Code mods guide builds a roughly 80-line Token Weather plugin from scratch that shows live context window usage above the prompt. It targets Claude Code 2.1.287 or later and covers event hooks, hot reload, state persistence, verification tests and plugin distribution.
Why it matters: A hands-on walkthrough that ties event hooks, state persistence and testing into reusable steps for customizing the Claude Code interface.
LangChain described how it built a model router inside the Agent Harness of Open SWE. In A/B tests, median cost per thread dropped 64%, with no measurable change in quality.
Why it matters: LangChain combines task analysis, model tiers and result tracking in agent routing, a reusable way to control model cost by task complexity.
Jev turns text classification into a general decision service that needs no per-task fine-tuning. The article traces the history of classification techniques and tests Jev's limits. On the 25,000-review IMDb test set, the Choice API hit 96.47% accuracy at a total cost of $0.6492. The article notes it cannot confirm whether the test set was part of the training data.
Why it matters: It compares Jev with bag-of-words models, ModernBERT and general LLMs, and lays out the cost and fit of direct cross-task classification versus fine-tuning a dedicated model.