Anthropic claims that 100% of its code is now written by AI. I can see this being perfectly valid. The model can be used even for the smallest task, like renaming the variable. We easily get to 100%. But the real question is how many tokens were used (wasted) during the process, and how much code with unnecessary cognitive load the model created.

Konrad Psiuk

Anthropic claims 100% of its code is now AI-written, which is technically achievable when AI assists with even trivial tasks like variable renaming. However, this raises important questions about token efficiency and whether AI-generated code introduces unnecessary complexity and cognitive overhead for developers.

100% of code written by AI

Coincidentally, Anthropic is a company that sells AI-based products.

An AI company claim their AI model works? This is huge and water is wet.

Writing code have never been the hardest part…

For the company that sells AI products and has ‘infinite’ access to the resources (tokens), it is so easy to make a “100% code written by AI” statement true. But without context and details, this is meaningless.

Agree. Today is about planning and knowing what you want.