Menu

Blog

Jan 13, 2023

ChatGPT: This AI has a JAILBREAK?! (Unbelievable AI Progress)

Posted by in categories: futurism, robotics/AI

ChatGPT, OpenAI’s newest model is a GPT-3 variant that has been fine-tuned using Reinforcement Learning from Human Feedback, and it is taking the world by storm!

Sponsor: Weights & Biases.
https://wandb.me/yannic.

OUTLINE:
0:00 — Intro.
0:40 — Sponsor: Weights & Biases.
3:20 — ChatGPT: How does it work?
5:20 — Reinforcement Learning from Human Feedback.
7:10 — ChatGPT Origins: The GPT-3.5 Series.
8:20 — OpenAI’s strategy: Iterative Refinement.
9:10 — ChatGPT’s amazing capabilities.
14:10 — Internals: What we know so far.
16:10 — Building a virtual machine in ChatGPT’s imagination (insane)
20:15 — Jailbreaks: Circumventing the safety mechanisms.
29:25 — How OpenAI sees the future.

References:
https://openai.com/blog/chatgpt/
https://openai.com/blog/language-model-safety-and-misuse/
https://beta.openai.com/docs/model-index-for-researchers.
https://scale.com/blog/gpt-3-davinci-003-comparison#Conclusion.

/photo/1

/photo/2

/photo/1

/photo/1

/photo/1

/photo/1

/photo/2

/photo/4

/photo/1

https://twitter.com/i/web/status/1598246145171804161


https://www.engraved.blog/building-a-virtual-machine-inside/

/photo/1

/photo/2

/photo/1

/photo/1

/photo/2

/photo/1

/photo/1

/photo/1

/photo/1

/photo/1

/photo/3

/photo/1

/photo/2
https://github.com/sw-yx/ai-notes/blob/main/TEXT.md#jailbreaks.

/photo/4

Links:
https://ykilcher.com.
Merch: https://ykilcher.com/merch.
YouTube: https://www.youtube.com/c/yannickilcher.
Twitter: https://twitter.com/ykilcher.
Discord: https://ykilcher.com/discord.

If you want to support me, the best thing to do is to share out the content smile

Comments are closed.