AITOPAI热报
ProductsMulti-source

Addy Osmani 加入 Claude Code 团队

关于 Addy Osmani 更多内容推荐 https://t.co/JKTkkWHyRo

shao__meng@shao__meng
Post· 11 sources
View the post
Why we picked it

Addy Osmani 加入 Claude Code，他是 AI 工程领域的重要人物，博客和书籍都很实用。

Addy Osmani 已加入 Anthropic 的 Claude Code 团队。他发表了多篇关于 Agent Harness、Skills 和 Agentic Engineering 的代表性博客。他的书籍《Beyond Vibe Coding》和 GitHub 上的"生产级工程 Skills"项目获得了 92.9K 星标。

Original · shao__meng

关于 Addy Osmani 更多内容推荐 https://t.co/JKTkkWHyRo

关于 Addy Osmani 更多内容推荐 x.com/shao__meng/sta… meng shao @shao__meng Addy Osmani 加入的是 Claude Code！ Addy 对 Agent Harness、Skills、Agentic Engineering、Loop Engineering 等 AI Engineering 重点知识都发表过很有代表性的博客： addyosmani.com/blog/ 书籍「Beyond Vibe Coding」也非常值得阅读 beyond.addy.ie 还有他的「生产级工程 Skills」92.9K 🌟 github.com/addyosmani/age… x 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 25 ⚡

  • Claude Code: GitHub Releases09-08 20:37原文
  • IT之家09-08 23:29原文
  • Tech in Asia09-10 04:42原文
  • The Business Times: Tech09-08 02:23原文
  • DeepLearning.AI09-08 20:00原文
  • arXiv: Anthropic09-09 01:56原文
  • 小互09-09 12:33原文
  • Anthropic09-09 13:33原文
  • The Rundown AI09-09 19:37原文
  • lmarena.ai09-09 20:02原文
#Claude Code#Addy Osmani#Agentic Engineering#AI工程

Keep reading

Recent stories with the same tag or section
ProductsBuildersMulti-sourceSelected02:19
Google launches Gemini API CLI for agent workflows

The stateless design flips the usual pattern: instead of another agent, Google ships a tool your current agent calls, keeping context ownership with Claude Code or Cursor. Developers building multi-tool agent pipelines can add Gemini's multimodal capabilities—video, speech, PDF analysis—without leaving their existing setup. It competes less with coding agents and more with direct SDK integrations, offering a uniform CLI interface any agent can invoke.

#Gemini#Google#CLI#agents
Event
Philipp Schmid@_philschmid3 sourcesSource
ProductsBuildersSelected23:13
Nace AI launches Drex for Search for agent document retrieval

The gains come from cutting agent steps and input tokens by more than half, which lowers API costs on retrieval-heavy workloads rather than just raising accuracy a few points. Teams building agents over enterprise document stores can plug it into Claude Code, Codex or Hermes Agent as a tool. The OfficeQA benchmark result offers a direct comparison point for evaluating retrieval layers before committing to one.

#Drex for Search#Nace AI#Claude Code#Codex
Event
TestingCatalog@testingcatalog2 sourcesSource
PapersBuildersSelected21:01
PostTrainBench exposes locked strategy in LLM training agents

The failure mode is not execution but the absence of a trigger to re-open strategy decisions mid-run, a finding that reshapes how agent benchmarks should be designed. Anyone building autonomous ML or post-training agents should plan checkpoints for human strategy input rather than longer budgets. Defaults also follow the harness, not the task — Claude Code picks full-parameter SFT 71.9% of the time while Codex CLI picks PEFT/LoRA 89.5% — so tool choice itself biases your pipeline.

#PostTrainBench#OpenBMB#Claude Code#Codex CLI
OpenBMB@OpenBMBSource