No, what I was trying to say was, try to learn and generalize something from how a smart mind could violate what you thought were the underlying axioms of the computing system to get at you, if it happened before Rowhammer had been discovered (by humans).
@esyudkowsky
-
Powerful Agents Optimize Against Lossy Approximations
By
–
They're lossy approximations, and we should expect more powerful agents to expend compute on avoiding the losses.
-
Bayesian Distributions Over Probabilities: Responding to Pedro’s Argument
By
–
Okay. I'll summarize for latecomers. Pedro, in the tones of somebody delivering a real zinger, said, "if you’re a true Bayesian you have a distribution over probabilities, and mine has its maximum at zero". It should first be noted that I know of no principle of Bayesianism
-
Bing Image Creator’s Subtle Watermark Strategy Praised
By
–
Oh hey, Bing Image Creator is still adding the easily removed watermark, it's just subtler. Good for OpenAI, I'm unironically glad they didn't just back down as soon as their competitors played it looser.
-
AI-driven job displacement may occur before end of decade
By
–
I think I have moved in the last 2 years toward "AI will disemploy some people before EOW". Still not sure I expect it to show up in GDP stats; the Internet and computers created some disemployment but didn't show up much in GDP stats.
-
Bet on AI risk probability increase against LeCun
By
–
I just bet M$10 on 4%->8%, I think LeCun is obviously wrong but not 25:1 worth of wrong.
-
Betting on Open-Source LLM Dominance by End of 2025
By
–
Sounds falsifiable. Want to bet? If so, when is 'soon' and what is 'unbeatable'? Throwing out possible terms in case it saves you trouble: 'Soon' is EOY 2025 and 'unbeatable' means that most spending/use of LLMs happens with models built on open-source foundations.
-
Disemployment vs Unemployment: AI Jobs and Policy Response
By
–
Disemployment is what happens when somebody loses their job. Unemployment is what happens when they can't find a new one. AI currently seems on course to produce disemployment; but it's bad monetary policy and labor policy that'd turn it into unemployment.
-
Fed’s Timing Risks Worsening AI-Driven Unemployment Crisis
By
–
Based on how Earth always does everything exactly the wrong way, I'm guessing the plan is to run inflation hot until the Federal Reserve takes drastic action to clamp down at exactly the point where AI disemployment starts to seriously hit large numbers of people.
-
HPMOR’s dangerous impact on AI alignment through reader influence
By
–
HPMOR specifically is famous for doing this to some readers! They're aiming their AI at one of the most dangerous targets!