rw-book-cover

Metadata

Highlights

  • Anthropic gave me access to a preview version of a “new model” over the weekend which turned out to be Sonnet 4.5. My initial impressions were that it felt like a better model for code than GPT-5-Codex, which has been my preferred coding model since it launched a few weeks ago. This space moves so fast—Gemini 3 is rumored to land soon so who knows how long Sonnet 4.5 will continue to hold the “best coding model” crown. (View Highlight)
  • Anthropic gave me access to a preview version of a “new model” over the weekend which turned out to be Sonnet 4.5. My initial impressions were that it felt like a better model for code than GPT-5-Codex, which has been my preferred coding model since it launched a few weeks ago. This space moves so fast—Gemini 3 is rumored to land soon so who knows how long Sonnet 4.5 will continue to hold the “best coding model” crown. (View Highlight)
  • The claude.ai web interface (not yet the Claude iPhone native app) recently added the ability for Claude to write and then directly execute code in a sandboxed server environment, using Python and Node.js. I wrote about that in detail three weeks ago. (View Highlight)
  • The claude.ai web interface (not yet the Claude iPhone native app) recently added the ability for Claude to write and then directly execute code in a sandboxed server environment, using Python and Node.js. I wrote about that in detail three weeks ago. (View Highlight)
  • Anthropic’s implementation of this code interpreter pattern is more powerful than ChatGPT’s equivalent because it can directly clone code from GitHub and install software packages from NPM and PyPI. (View Highlight)
  • Anthropic’s implementation of this code interpreter pattern is more powerful than ChatGPT’s equivalent because it can directly clone code from GitHub and install software packages from NPM and PyPI. (View Highlight)
  • Sonnet 4.5 absolutely shines at using this tool! (View Highlight)
  • Sonnet 4.5 absolutely shines at using this tool! (View Highlight)
  • I released llm-anthropic 0.19 adding support for the new model. Then I ran my classic pelican benchmark, first with thinking turned on: (View Highlight)
  • I released llm-anthropic 0.19 adding support for the new model. Then I ran my classic pelican benchmark, first with thinking turned on: (View Highlight)
  • These are pretty good—they are recognizably pelicans!—though not quite as good as GPT-5-Codex which is better at drawing bicycles. (View Highlight)
  • These are pretty good—they are recognizably pelicans!—though not quite as good as GPT-5-Codex which is better at drawing bicycles. (View Highlight)
  • Anthropic also shipped a new Claude Code VS Code extension today, plus a big upgrade to the Claude Code terminal app. Plus they rebranded their confusingly named Claude Code SDK to the Claude Agent SDK instead, emphasizing that it’s a tool for building agents beyond just customizing the existing Claude Code product. That’s available for both TypeScript and Python. (View Highlight)
  • Anthropic also shipped a new Claude Code VS Code extension today, plus a big upgrade to the Claude Code terminal app. Plus they rebranded their confusingly named Claude Code SDK to the Claude Agent SDK instead, emphasizing that it’s a tool for building agents beyond just customizing the existing Claude Code product. That’s available for both TypeScript and Python. (View Highlight)