Optimality is the tiger, and agents are its teeth - LessWrong
lesswrong.com · 11,359 words · saved by 3 readers
You've done it. You've built the machine. …
x Optimality is the tiger, and agents are its teeth — LessWrong Best of LessWrong 2022 Optimization Agency AI Frontpage 352 Optimality is the tiger, and agents are its teeth by Veedrac 2nd Apr 2022 AI Alignment Forum 19 min read 46 352 Ω 71 You've done it. You've built the machine. You've read the AI safety arguments and you aren't stupid, so you've made sure you've mitigated all the reasons people are worried your system could be dangerous, but it wasn't so hard to do. AI safety seems a tractable concern. You've built a useful and intelligent system that operates along limited lines, with spe
saved by
related reading
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- Simulators — LessWronglesswrong.com
- What failure looks like — LessWronglesswrong.com
- Cyborgism — LessWronglesswrong.com
- The Machines Lack Honour — LessWronglesswrong.com
- Embedded Agency (full-text version) — LessWronglesswrong.com
- And Yet It Understandsborretti.me
- On AutoGPT — LessWronglesswrong.com
- The Problem — LessWronglesswrong.com
- why assume AGIs will optimize for fixed goals? — LessWronglesswrong.com
- Artificial General Intelligence and how (much) to worry about itstrangeloopcanon.com
- Many arguments for AI x-risk are wrong — AI Alignment Forumalignmentforum.org