Uploaded March 2023 | Updated September 2026, 1 hour ago
ChatGPT can only go so far, let's talk about the limitations of LLMs and topics like grounding and exploration that are important research directions for future work.
GTC Signup: nvda.ws/408jS7w
Raffle Signup: https://forms.gle/NyxKRw2tF6Un9CaT6
Sessions I'm attending:
- bit.ly/nvidia-science
- bit.ly/nvidia-real-world-rl
Outline
0:00 - Intro
0:48 - GPU Giveaway
1:06 - Human-Level AI
2:38 - My Thoughts on ChatGPT
3:52 - ChatGPT a Dead End
5:23 - Path Forward - AI Feedback
8:17 - Path Forward - Grounding
9:11 - Beyond LLMs
10:23 - GTC & Giveaway
11:37 - Outro
Social Media
YouTube - youtube.com/c/EdanMeyer
Twitter - twitter.com/ejmejm1
Sources:
ChatGPT: openai.com/blog/chatgpt
Anthropic AI Paper: anthropic.com/constitutional.pdf
ChatGPT can only go so far, let's talk about the limitations of LLMs and topics like grounding and exploration that are important research directions for future work.
GTC Signup: nvda.ws/408jS7w
Raffle Signup: https://forms.gle/NyxKRw2tF6Un9CaT6
Sessions I'm attending:
- bit.ly/nvidia-science
- bit.ly/nvidia-real-world-rl
Outline
0:00 - Intro
0:48 - GPU Giveaway
1:06 - Human-Level AI
2:38 - My Thoughts on ChatGPT
3:52 - ChatGPT a Dead End
5:23 - Path Forward - AI Feedback
8:17 - Path Forward - Grounding
9:11 - Beyond LLMs
10:23 - GTC & Giveaway
11:37 - Outro
Social Media
YouTube - youtube.com/c/EdanMeyer
Twitter - twitter.com/ejmejm1
Sources:
ChatGPT: openai.com/blog/chatgpt
Anthropic AI Paper: anthropic.com/constitutional.pdf
![ML Research Idea [Zero to Paper]](https://i.ytimg.com/vi/nSEb6w_BBqE/mqdefault.jpg "ML Research Idea [Zero to Paper]
This episode (part 2) of Zero to Paper covers the idea we will be working on: Text to Goal, or TTG for short. TTG aims to translate natural language into a reward function for a Reinforcement Learning problem. This research project aims to leverage recent advancements in NLP and Computer Vision to make reward functions easier and more natural to craft.
I also briefly touch on how I come up with ideas an what is important to me. I hope this will be helpful to anyone wonder how to do ML research!
Zero to Paper playlist: https://www.youtube.com/watch?v=74fKCvr5n5o&list=PL_49VD9KwQ_ONxENRk11jFEI3_pqAwaug
RL Theory series if you want to get into RL: https://www.youtube.com/watch?v=1OI0uuz9jkI&list=PL_49VD9KwQ_OML1Knh-Yb7FUFkhTLS0jL")
