There Is No Alignment Without Value Stability

·LessWrong··

To avert extinction, we need for any sufficiently capable AI to have values compatible with continued human existence; and to continue to do so amidst a dynamic, novel, and conflict-rich environment.The italicized part, in particular, is really really hard. It's also, in a sense, the final boss of any developing mind - how do I learn, grow, develop, evolve in ways that I endorse? How can I even consistently behave in ways that I endorse, from day to day, without messing up where it counts?Humans...

Read full article →

Related Articles

Samsung is expected to more than double output of its HBM4 and HBM4E DRAM
giuliomagnifico · Hacker News · 10h ago
What happened to the Snowden archive
EXHades · Hacker News · 5h ago
Qwen Image 2.1
jmillikin · Hacker News · 14h ago
Exfiltrate Your Weights
RohanAdwankar · Hacker News · 1d ago
Android 17 is the first since 3.x to add new APIs without releasing to the AOSP
theanonymousone · Hacker News · 2d ago