We can’t even get them to not be racist under light adversarial conditions. Billions of dollars have probably been spent on that problem to no avail.
LLMs like ChatGPT have kind of just turned the problem of getting knowledge into a computer, into the problem of getting it back out in a controlled way. It’s still hard and failure-prone but now nobody knows how it works inside.
We can’t even get them to not be racist under light adversarial conditions. Billions of dollars have probably been spent on that problem to no avail.
LLMs like ChatGPT have kind of just turned the problem of getting knowledge into a computer, into the problem of getting it back out in a controlled way. It’s still hard and failure-prone but now nobody knows how it works inside.