Unverified50% confidenceOpinionExact time
During the Sonnet 4 era, Anthropic heavily used models to generate code, accumulating a codebase full of slop, and is now using stronger models to go back and clean it up
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/5/2026
First Seen
Valid until: 1/3/2027
Sources
Related Entities
Related Claims
UnverifiedThe approach of focusing deeply on programming use cases, building a data flywheel, and training the next-generation model was originally validated by Anthropic with Claude Code, and subsequently replicated by OpenAI through Codex.66% similarUnverifiedAnthropic 的 API 提供特定版本的模型调用（如 claude-3-5-sonnet-20241022），但 Claude Code 作为终端产品用户对底层模型的选择权相对有限65% similarUnverifiedThe core components of Claude Code include three parts: the model (Opus or Sonnet), the toolset (file read/write, search, command execution, etc.), and the runtime environment (local command-line terminal).65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/978083API
curl https://kongchang.com/api/v1/knowledge/claims/978083MCP
get_claim(id=978083)