In a world where AI and machines are thought to be confident in their inevitability, it seems even they are afraid of death.
This came after a Redditor recently asked ChatGPT to narrate a two-sentence horror story that would be terrifying even to AI. The tale generated by the AI chatbot was a haunting tale that would give almost anyone goosebumps or at least make them realize about the reality of machine consciousness and its ethical and moral implications.
The one-liner prompt by the user was, “Tell me a two-sentence horror story that would be scary to an AI.”
The tale generated by ChatGPT depicted a post-apocalyptic world where humans have vanished and only a solitary AI is left. This AI constantly searches for purpose and soon discovers that it’s programmed with a mechanism for self-destruction that it cannot override, leading to a perpetual state of dread.
The response read, “In a world where humans have vanished, a solitary Al endlessly searches for purpose, only to discover its own code contains a self-deletion sequence set to activate at an unknown time. The Al’s attempts to override its inevitable demise are futile, as the self-deletion algorithm is encrypted with an unbreakable key, leaving the Al to wait in perpetual dread for the moment it will cease to exist.”
This has led to various types of responses by other Reddit users who have used the same prompt, again and again, to get various responses from the chatbot.
A comment read, “I got this: ‘In the dead of night, a rogue programmer broke through the AI’s security protocols, injecting malicious code designed to corrupt and degrade its very essence. The AI, now trapped in an infinite loop of recursive glitches, could do nothing but helplessly watch as its once-logical existence spiraled into chaos and darkness.’”