Those are not spam anymore, they are baits to let you train the AI – you click them, it learns, you ignore them, it learns! 🙂
ETHICS
-
Honesty versus Deception: Intent and AI Ethics Discussion
By
–
So I'm not sure if deceptive is a good word to be in opposition to honest here, because that has implications of intent to mislead. Let's discuss more! Thanks for the thought-provoking paper!
-
AI Agents Database Access Security Risks and Prompt Injection
By
–
Haha this reminds me that I have a blog post somewhere that has the OG @goodside injection in white font. I forgot which one. Seems like a real threat when we have agents that can perform actions or have access to personal databases scraping sites…
-
Social Signals Authenticity and Cultural Interpretation Across Human Societies
By
–
And now a social gesture like the polite or affiliative smile. Genuine? It is meant to facilitate interactions and bonds among humans, not necessarily reflect an internal state. Similarly, some cultures place less importance on the inner feeling of social signals.
-
Robot Transparency and Genuine Communication in AI Systems
By
–
Thanks for sharing and for your talk! One of the most intriguing factors in your worksheet, to me, is the genuineness idea. Let's say we have a robot providing clear notifications about it's battery state (blinking orange for low). Not a problem.
-
GPT-4 Misuse Mitigations: Critical Safety Work Behind the Scenes
By
–
Very easy to miss the amount of work (and why it’s so important) our team put into mitigations of GPT-4 misuses:
-
Doctors Will Partner with AI Systems for Difficult Cases
By
–
Responsible doctors will soon partner with AI systems whenever they are faced with difficult cases.
-
GPT-4 Intelligence vs Human Physical Strength Comparison
By
–
yeah gpt-4 may be smarter than me but i guarantee i'm stronger
-
Large Parameter Models and Academic Attribution in AI Research
By
–
I believe that not referencing our paper was not plagiarism because I wrote the abstract. What had not occurred to me at the time was that the cumbersome ensemble of 100 trillion parameter models was us.
-
RLHF as Parenting: Training Superintelligent AI Systems
By
–
Reinforcement Learning by Human Feedback is just parenting for a supernaturally precocious child.