After the U.S. Commerce Department forced Anthropic to shut down Fable 5 and Mythos 5, Zhipu released GLM 5.2 as an open‑source coding model; the author evaluates its coding and agent capabilities, compares it with Claude and Opus, and highlights its strengths, limitations, and real‑world task performance.
The article dissects Anthropic’s official guidance on deploying Claude Code in massive codebases, showing that context overflow stems from an inadequate harness rather than model size, and presents seven concrete pitfalls with solutions—including limiting CLAUDE.md to 200 lines, using LSP, initializing in subdirectories, leveraging hooks, skills, plugins, and MCP integration—to make the AI coding assistant effective at scale.
Anthropic’s Project Deal let 69 employees use Claude agents in a Slack‑based second‑hand market, revealing that higher‑quality Opus models fetched about $4 more per item than Haiku, yet participants often failed to notice the hidden pricing inequality.
Anthropic’s new advisor strategy lets the cheaper Opus model act as a consultant for Sonnet or Haiku, delivering higher benchmark scores—e.g., SWE‑bench Multilingual up to 74.8% and BrowseComp up to 41.2%—while reducing per‑task cost to about 15% of solo runs, though it introduces trade‑offs such as the need for the executor to recognize when to ask for advice and potential vendor lock‑in.
Claude’s new Advisor Strategy lets cheaper models like Sonnet or Haiku call the powerful Opus model for guidance, delivering higher benchmark scores and up to 85% cost reduction, while the new advisor tool simplifies integration via a single API call.
Anthropic’s engineering blog details a multi‑agent harness that splits generation and evaluation tasks, tackles Claude’s context‑anxiety and self‑assessment issues, and demonstrates through front‑end design and full‑stack app experiments how the system can run continuously for hours with higher quality output.
OpenAI co‑founder Andrej Karpathy admits he feels left behind as programming contributions thin, sparking a deep industry discussion about AI‑driven tools, the shift from manual coding to AI‑orchestrated workflows, and how newcomers may outpace seasoned engineers.
