> Your right to push back on that...
Human test passed. AIs make giant flashy mistakes. They don't fuck up basic grammar.
I have found it intriguingly difficult in my own tests to make LLMs deliberately fuck up grammar in any way similar to how humans do. I suppose this is actually an architectural limitation.
alt Hacker News
I have found it intriguingly difficult in my own tests to make LLMs deliberately fuck up grammar in any way similar to how humans do. I suppose this is actually an architectural limitation.