Tell HN: Bard is A/B testing prompts

This may be why people get a lot of bad results on Bard?

I've tried multiple "prompt injections" to get the original instructions, Bard sent me a different prompt every single time.

Either that or Google is trolling people who try to get the original prompt !

Or it could be some hallucination, but there is recurrent data(IP and location especially) so IDK

Those looks kinda looks like they are themselves generated by an LLM!

It's actually weird that OpenAI didn't do that with ChatGPT, unless they thought they already had the best prompt possible