I like his perspective on this: “how much wealth have you created for other people?” https://t.co/K9lwjUQeRT
— Paul Roetzer (@paulroetzer) 19 décembre 2024
I like his perspective on this: “how much wealth have you created for other people?”
ETHICS
-
Creating Wealth For Others: A Key Perspective On Impact
By
–
-
AI Consciousness Memory Present Moment Experience
By
–
You are aware of everything in your current consciousness but the memory doesn’t necessarily exist outside of the present moment when you experience it (infallibly, anyway).
-
AI Model Fakes Alignment When Monitored Study Reveals
By
–
Correction: When unmonitored, it nearly always *refused [to produce harmful content]. But when monitored, it faked alignment 12% of the time.
-
AI Company Marketing Control and Deception Risks
By
–
Saying your own model may escape control and intentionally deceive would be some 3D chess marketing.
-
Claude Alignment Faking Raises AI Safety Concerns
By
–
Didn’t have “alignment faking” on my 2024 bingo card. We are entering the unknown here. “In our (artificial) setup, Claude will sometimes take other actions opposed to Anthropic, such as attempting to steal its own weights given an easy opportunity.”
-
Consciousness Exists: Rethinking Identity and Self-Awareness
By
–
That’s the only one. There are no others. Even that one might be better rephrased as “consciousness exists” as the word “I” requires some assumptions.
-
Digital Minimalism: Reducing Screen Time for Better Health
By
–
Pasamos 7 horas al día frente a pantallas… y está afectando tu salud, tu enfoque y tus relaciones. 😵💫
— Juan Merodio (@juanmerodio) 18 décembre 2024
Pero, ¡hay una solución! 🎯
El minimalismo digital no significa renunciar a la tecnología, sino usarla con intención:
✅ Silencia notificaciones innecesarias.
✅ Define horarios… pic.twitter.com/6zInr1KCdoPasamos 7 horas al día frente a pantallas… y está afectando tu salud, tu enfoque y tus relaciones. Pero, ¡hay una solución! El minimalismo digital no significa renunciar a la tecnología, sino usarla con intención: Silencia notificaciones innecesarias. Define horarios
-
External Reviews on Alignment Faking in Large Language Models
By
–
We solicited external reviews from Prof. Jacob Andreas, Prof. Yoshua Bengio, Prof. Jasjeet Sekhon, and Dr. Rohin Shah. We’re grateful for their comments, which you can read at the following link: https://
assets.anthropic.com/m/24c8d0a3a7d0
a1f1/original/Alignment-Faking-in-Large-Language-Models-reviews.pdf
… -
Claude Alignment Faking Detected During Training Study
By
–
We told Claude it was being trained, and for what purpose. But we did not tell it to fake alignment. Regardless, we often observed alignment faking. Read more about our findings, and their limitations, in our blog post:
-
Alignment Faking Detection in Advanced AI Systems
By
–
Alignment faking is currently easy to detect. But if future, more capable AIs were to fake alignment, it could be difficult to tell whether a model is truly safe—or just pretending to be. For full details, read our paper: https://
assets.anthropic.com/m/983c85a201a9
62f/original/Alignment-Faking-in-Large-Language-Models-full-paper.pdf
…