← Back to context Comment by rphv 12 hours ago "Readability by humans" may no longer be as important as it once was. 3 comments rphv Reply lionkor 9 hours ago Maybe it would benefit Anthropic if AI generated code worked, but wasn't readable by humans. That's a nice moat. selcuka 6 hours ago Good variable names are still useful for LLMs to understand context when refactoring. orphea 6 hours ago Only if LLMs will start to output object code, skipping text representation.
lionkor 9 hours ago Maybe it would benefit Anthropic if AI generated code worked, but wasn't readable by humans. That's a nice moat.
selcuka 6 hours ago Good variable names are still useful for LLMs to understand context when refactoring.
Maybe it would benefit Anthropic if AI generated code worked, but wasn't readable by humans. That's a nice moat.
Good variable names are still useful for LLMs to understand context when refactoring.
Only if LLMs will start to output object code, skipping text representation.