Uploaded September 2021 | Updated September 2026, 6 hours ago
OpenAI Codex is OpenAI's latest GPT-based language based model that generates code. In this video we test if Codex can remake a model like itself, a code generation model. Given that this is similar to the condition to start the singularity, I thought it would be interesting to test how far it could get.
Previous video on OpenAI Codex: youtu.be/FC962DmVfSU
Next video on OpenAI Codex: youtu.be/Pkp1MRFGUVo
Link to API post: openai.com/blog/openai-codex
OpenAI Codex is OpenAI's latest GPT-based language based model that generates code. In this video we test if Codex can remake a model like itself, a code generation model. Given that this is similar to the condition to start the singularity, I thought it would be interesting to test how far it could get.
Previous video on OpenAI Codex: youtu.be/FC962DmVfSU
Next video on OpenAI Codex: youtu.be/Pkp1MRFGUVo
Link to API post: openai.com/blog/openai-codex
![Self-Supervised RL - Learning Without Data [Zero to Paper]](https://i.ytimg.com/vi/CDKsa06xU0o/mqdefault.jpg "Self-Supervised RL - Learning Without Data [Zero to Paper]
Inverse Reinforcement Learning with Natural Language Goals (LangGoal IRL) offers a way to do sample-efficient IRL and a way to generalize using self-supervised learning. The paper is novel and is a step forward for general AI and ML algorithms. Though it has its cons, I think it is one of the better papers out there that cover RL, IRL, NLP, and generalization.
Zero to Paper playlist: https://www.youtube.com/playlist?list=PL_49VD9KwQ_ONxENRk11jFEI3_pqAwaug
Inverse Reinforcement Learning video: https://www.youtube.com/watch?v=qo355ALvLRI
Paper covered: https://arxiv.org/pdf/2008.06924.pdf")
