@gcolbourn @Zai_org I still feel that we face unacceptable and catastrophic risks linked to human misuse and conflict between human-controlled entities who can direct AGIs to pursue their goals at all costs (as the Vending-Bench system prompt directs).
same thread: 2021691875128692747 2021707718399336721 2021709270723477584 2021711019853435225 2021716404177666449 2021717576997380570 2021718455590830081 2021719872783163512 2022321566420197730 2022322819258823088 2022327878051127766 2022328885317353712
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.