Tag
OpenAI shares how engineers use Codex's Ultrafast mode internally to cut incident investigation from hours down to 10-15 minutes, with near real-time answers from multiple data sources and faster code refactoring.
Imprint shares how its `small-change` approach speeds up pull request review, explaining eligibility criteria and the reasoning behind rethinking review purposes as PR volume and review times grow.
Pragmatic Engineer 作者 Gergely Orosz 与 Uber 资深工程师 Uday Kiran Medisetty 带领观众了解 Uber 内部高度定制化的开发者工具体系，涵盖 DevPods、面向 AI agent 的构建、MCP gateway、Model Gateway、Agent Skills 仓库以及 PR 分类衡量方式等。
Gergely Orosz highlights the hidden complexity of agentic AI systems inside mid-sized and larger companies, noting limited AI context windows versus massive internal context, and teases an upcoming Pragmatic Engineer case study on Uber's 19 internal custom AI-related systems.
A LoRA adapter was trained on an abliterated Qwen 3.8-27B model to enhance internal codebase recall, demonstrating superior performance over Claude models on private-repo-specific tasks in evaluations.