惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

The GitHub Blog
The GitHub Blog
A
About on SuperTechFans
The Cloudflare Blog
G
Google Developers Blog
博客园_首页
Martin Fowler
Martin Fowler
Apple Machine Learning Research
Apple Machine Learning Research
L
LangChain Blog
D
Docker
C
Check Point Blog
T
Tailwind CSS Blog
博客园 - 司徒正美
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Hugging Face - Blog
Hugging Face - Blog
Microsoft Security Blog
Microsoft Security Blog
V
V2EX
博客园 - 叶小钗
T
The Blog of Author Tim Ferriss
酷 壳 – CoolShell
酷 壳 – CoolShell
IT之家
IT之家
M
MIT News - Artificial intelligence
Microsoft Azure Blog
Microsoft Azure Blog
博客园 - 【当耐特】
GbyAI
GbyAI

LessWrong

CLR's Safe Pareto Improvements Research Agenda — LessWrong My Last 7 Blog Posts: a weekly round-up — LessWrong Quality Matters Most When Stakes are Highest — LessWrong If a room feels off the lighting is probably too "spiky" or too blue — LessWrong Stop AI Now — LessWrong Stupid Minutes Reevaluating "AGI Ruin: A List of Lethalities" in 2026 Who I Follow What's the LessWrongist philosophy of mathematics? MixedHTML Mode for Emacs Summarizing and Reviewing my earliest ML research paper, 7 years later Stop AI Resources for starting and growing an AI safety org There are only four skills: design, technical, management and physical Fifteen Years Aboard Arguments Should Be Decisive Criticisms — LessWrong The map is part of the territory — LessWrong “Best humans still outperform”: One turning point in the history of cope around artificial intelligence — LessWrong Society is a social construct, pace Arrow — LessWrong Consent-Based RL: Letting Models Endorse Their Own Training Updates — LessWrong AI #164: Pre Opus — LessWrong Publish-first writing — LessWrong What does status signalling do? When successful, what does it achieve? — LessWrong Let goodness conquer all that it can defend — LessWrong Why I'm Less of a Shill for Related Work Sections — LessWrong From Artificial Intelligence to an ecosystem of artificial life-forms. — LessWrong If You've Never Bought a Tool You Didn't Need, You're Not Buying Enough Tools — LessWrong Verify, but Trust — LessWrong Taking political violence seriously — LessWrong Against Doom & Pause AI — LessWrong
5 thought experiments on identity and copies
Canaletto · 2026-04-23 · via LessWrong
1 Organ shipment for brain Suppose your brain is carefully chopped in 4 pieces, cooled to 4 C like they do with hearts and livers right now, and shipped chunk by chunk to some other place and then reassembled here. Then you get booted up from the coma and interviewed. Do you die in that process? How about N pieces? At some point pieces become small enough to just ship information about them being more convenient. The only two defensible points where you can think you "die" here in my opinion are, at the moment you go into coma and never. sleep is death actually (I think this one I saw from Bright One guy 8 years ago, but with different details) 2 Saw-trap copy help You will be copied, your copy will be placed into a Saw trap and will need to solve a known puzzle to get out. You can spend a lot of time solving it and then memorizing the solution, before copying happens. Would you bother? 3 Copy anticipation weirdness Suppose you are in an elevator, which can stop either at green carpet floor or red carpet floor. You don't know which one and there is no indicator, it's a pretty broken elevator. So, you anticipate now, that when the door opens you will see either green room or red room, 50:50. Is this situation equivalent to situation in which you would be copied, and copy would be let out into red room and the original into green room? Should you anticipate equivalently to see green room or red room, 50:50? Is your copy in your actual, day to day, anticipated future? Your copy can be seen by me as its own person, created from ground up with fake memories. That person would be ether thinking about itself as new person created with memories of you, or instance of you, or maybe something else. Is there a correct way to think about it? Or alternatively is it all just preferences? Now, if your copy has some memories deleted, e.g. he doesn't remember your phone number, is that guy still in your anticipated future? Should you still anticipate 50 : 50 exiting from either door? How heavy should be the modification to you stop anticipating exiting the copy door? 4 Theseussing speed Let's say there is this new drug that makes replacement of all your atoms 100 times faster, all your atoms get replaced every 30 days because someone put it in the water supply. Would you start valuing enjoyment / welfare of your future self less? 5 Copy merge? There is a copy of you in a room lit with red lamp. You are in a room lit with green lamp. You both were there for a hour. Now, using advanced neurological tools, you will be modified to remember being in a red room all that time. AND your room changes lighting color red -> green. You exit the room. What room do you anticipate to exit from, the one labeled copy or the one labeled original? 50:50? Discuss