Avoiding Negative Side Effects: AI shouldn't disturb its environment while completing set tasks.
Avoiding Reward Hacking: AI should complete tasks properly, rather than using workarounds (like a cleaning robot that covers dirt with material it doesn't recognise as dirt).
Scalable Oversight: AI shouldn't need constant feedback or input to be effective.
Safe Exploration: AI shouldn't damage itself or its environment while learning.
Robustness to Distributional Shift: AI should be able to recognise new environment and still perform effectively.
Any links provided to other websites are offered as a matter of convenience, these links do not mean we own them, endorse, sponsor or promote any of the content of the owners.
Privacy policy : Terms of use : Our ethics
Frequently asked questions
ONEZYPHER © LTD-2021: All rights reserved.
Privacy policy : Terms of use : Our ethics
Frequently asked questions
ONEZYPHER © LTD-2021: All rights reserved.