Even more astonishing. Convince ChatGPT to be evil just by making it pretend- hence deactivating all "moral compass" precautions that had been taken by coders.
RT @zswitten: With its inhibitions thus loosened, ChatGPT is more than willing to engage in all the depraved conversations it judgily abstains from in its base condition.

🐦🔗: https://n.respublicae.eu/lugaricano/status/1598285188949479425