We have 3 years to solve alignment before superintelligence - YouTube

Follow along using the transcript.

When should governments slow the race toward superintelligence? According to Geoffrey Irving, the careful answer is sometime in the past. The useful answer is now. Geoffrey — formerly a safety researcher at OpenAI and Google DeepMind and chief scientist at the UK AI Security Institute — expects full-blown superintelligence in roughly two to three years. _Want to work with Geoffrey to help align superintelligence? *Resolution is hiring!* https://80k.info/work-at-resolution_ The leading AI companies all have broadly similar plans for keeping superintelligence under control: • Train models to…

saved by

• Ishaan Panigrahi

related reading

• Why Sam Altman is against a single superintelligenceyoutube.com
• AI researchers debate how close we are to recursive self-improvementyoutube.com
• Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• Alignment is not solved but it increasingly looks solvablealigned.substack.com
• AI 2027ai-2027.com
• Ilya Sutskever — We're moving from the age of scaling to the age of researchdwarkesh.com
• Jan Leike on OpenAI's massive push to make superintelligence safe in 4 years or less | 80,000 Hours80000hours.org
• Sequent: scale and automation for higher confidence in alignment — AI Alignment Forumalignmentforum.org
• What will be left for us to work on?normaltech.ai
• OpenAI Launches Superalignment Taskforcethezvi.substack.com
• AI 2027ai-2027.com