In MWI some part of the body always remains. But why destuctible?
avturchin on Quantum Immortality: A Perspective if AI Doomers are Probably RightI think that first perspective is meaningful as it allows me to treat my self as a random sample from some group of minds.
ramblindash on Should CA, TX, OK, and LA merge into a giant swing state, just for elections?Sorry
philosophicalsoul on Thomas Kwa's ShortformAnswering this from a legal perspective:
philosophicalsoul on Saul Munn's ShortformWhat is the easiest and most practical way to translate legalese into scientifically accurate terms, thus bridging the gap between AI experts and lawyers? Stated differently, how do we move from localised papers that only work in law or AI fields respectively, to papers that work in both?
Glad somebody finally made a post about this. I experimented with the distinction in my trio of posts on photographic memory a while back.
wassname on Model Organisms of Misalignment: The Case for a New Pillar of Alignment ResearchTo the people disagreeing, what part do you disagree with? My main point, or my example? Or something else
philosophicalsoul on Does LessWrong make a difference when it comes to AI alignment?I was naive during the period in which I made this particular post. I'm happy with the direction LW is going in, having experienced more of the AI world, and read many more posts. Thank you for your input regardless.
kaj_sotala on Should CA, TX, OK, and LA merge into a giant swing state, just for elections?As far as I know, the latest representative expert survey on the topic is "Thousands of AI Authors on the Future of AI", in which the median time for a 50% chance of AGI was either in 23 or 92 years, depending on how the question was phrased:
If science continues undisrupted, the chance of unaided machines outperforming humans in every possible task was estimated at 10% by 2027, and 50% by 2047. [...] However, the chance of all human occupations becoming fully automatable was forecast to reach 10% by 2037, and 50% as late as 2116 (compared to 2164 in the 2022 survey).
Not that these numbers would mean much because AI experts aren't experts on forecasting, but it still suggests a substantial possibility for AGI to take quite a while yet.
richard_kennaway on What are the primary drivers that caused selection pressure for intelligence in humans?Or briefly, intelligence is good for everything.
poignardazur on A basic systems architecture for AI agents that do autonomous researchI don't find that satisfying. Anyone can point out that a perimeter is "reasonably hard" to breach by pointing at a high wall topped with barbed wire, and naive observers will absolutely agree that the wall sure is very high and sure is made of reinforced concrete.
The perimeter is still trivially easy to breach if, say, the front desk is susceptible to social engineering tactics.
Claiming that an architecture is even reasonably secure still requires looking at it with an attacker's mindset. If you just look at the parts of the security you like, you can make a very convincing-sounding case that still misses glaring flaws. I'm not definitely saying that's what this article does, but it sure is giving me this vibe.