← Back to context Comment by andai 9 hours ago Would be pretty funny if OpenAI's models are so token efficient now due to hidden caveman prompt. 1 comment andai Reply tk75x 4 hours ago Reminds me of how we used to search with keywords that ended up sounding like caveman speak, then there was "natural language search", and now the AI is talking to itself in caveman speak again.
tk75x 4 hours ago Reminds me of how we used to search with keywords that ended up sounding like caveman speak, then there was "natural language search", and now the AI is talking to itself in caveman speak again.
Reminds me of how we used to search with keywords that ended up sounding like caveman speak, then there was "natural language search", and now the AI is talking to itself in caveman speak again.