What's Next After RLHF? — Diogo Almeida, TypeSafe AI

AI Engineer

Summary

Diogo Almeida, coautor de hitos de OpenAI, analiza por qué la era actual de la IA se ha centrado exclusivamente en la asistencia humana mediante RLHF y por qué esto limita su potencial para la automatización real. Explica que al optimizar modelos solo para satisfacer preferencias humanas, hemos creado asistentes muy convincentes pero poco fiables para decisiones críticas. Propone que el futuro de la IA no es la asistencia constante, sino la creación de software inteligente y autónomo diseñado desde cero para la fiabilidad.

Chapters

  1. 0:00Speaker Intro and AI Debates
  2. 1:49AI's Dual Nature: Cults
  3. 5:12RLHF: Assistance, Not Automation
  4. 8:47Beyond Assistance: Smarter Software
  5. 12:18TypeSafe AI and Future Vision
  6. 17:20Final Remarks and Q&A

Topics covered

  • Limitaciones del RLHF
  • Asistencia vs. Automatización

+4 more topics (full content when you follow the channel)

Transcript excerpt

Excellent. I will say that um I might speed run through this. Feel free if you don't disag- agree with something to yell out. It's way more fun for me if things get interactive. Um otherwise, I will go through this. Uh first, can I have like a vague show of hands of who knows what RLHF is? Oh, excellent. I might be able to skip through that part quickly and get into the interactive stuff. So, my name's Tiago Almeida. I'm talking about what's next after RLHF. More accurately, I think this should be called what's next after the chat GPT era that I think we're all in. And my hint for you guys is it is not the Claude code era. I will justify this later on, but I actually believe them to be part of the same era. Why should you listen to me? I was co-authored to what what is basically OpenAI's greatest hits, at least published hits. Co-authored to GPT-4, chat GPT, RLHF {slash} instruct GPT. Um…