IIIc. Superalignment - SITUATIONAL AWARENESS
Reliably controlling AI systems much smarter than we are is an unsolved technical problem. And while it is a solvable problem, things could very easily go off the rails during a rapid intelligence explosion. Managing this will be extremely tense; failure could easily be catastrophic. The old sorcererHas finally gone away!Now the spirits he controlsShall
Reliably controlling AI systems much smarter than we are is an unsolved technical problem. And while it is a solvable problem, things could very easily go off the rails during a rapid intelligence explosion. Managing this will be extremely tense; failure could easily be catastrophic. In this piece: Toggle The old sorcerer Has finally gone away! Now the spirits he controls Shall obey my commands. … I shall work wonders too. … Sir, I’m in desperate straits! The spirits I summoned – I can’t get rid of them. Johann Wolfgang von Goethe, “The Sorcerer’s Apprentice” By this point, y
Explore this link on the map →related reading
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Quotes from Leopold Aschenbrenner's Situational Awareness Paperthezvi.substack.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- AI 2027ai-2027.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- OpenAI Launches Superalignment Taskforcethezvi.substack.com
- Jan Leike on OpenAI's massive push to make superintelligence safe in 4 years or less | 80,000 Hours80000hours.org
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- AI 2027ai-2027.com
- Alignment remains a hard, unsolved problem — AI Alignment Forumalignmentforum.org
- AI 2027ai-2027.com