alt Hacker News> People who (carefully) use it as an extension of their own mind and senses will very likely thrive, and those who use it as a replacement for their minds and their senses will struggle.
Claude code is entirely vibed. Someone posted some of the prompts they used: barely comprehensible typo-addled half phrases.
This seems to be the opposite of your experience.
I am sure some variant of the infinite monkey theorem applies. Anthropic devs have unlimited access to Claude, so they are no doubt lazy when it comes to prompt writing and just brute-force the agent to do what they want.