On: Medical chatbot using OpenAI’s GPT-3 told a fake p...

[908B64B197]

I didn't know it was made for a joke conference!

But it does illustrates how it's easy to get trapped into a local minima.

[wizzwizz4 → 908B64B197]

They're doing what you tell them to, not what you want them to. Same with GPT-3; it's predicting what (from its experience) it thinks a human would say, not what is ethical to say.

[rmrfrmrf → wizzwizz4]

unless...