Some observations about LLM's:
• Math: Can't really do math, doesn't have any model for it
• Research: Makes stuff up, can't be trusted, is extremely confident
• Coding: Unless it hits the correct example somewhere else, will usually get it wrong
• Data Analysis: fakes it until it makes it, but breaks down at any kind of scale
• Writing: as likely as not to plagiarize in ways that are hard to predict
If this was an employee or intern, I'd fire it. ;)
@davetroy I've actually been startled by how good it is at math. Granted, I haven't hit it with a huge battery of problems. And it does have the problem that if you're asking it to solve a problem, you, the asker, might not have enough domain knowledge to know when it makes a mistake.
