Common machine learning systems are starting to deploy the RL lens of feedback.
This is a really good summary. Really enjoy your writing style. I've been trying to cover the ChatGPT and Davinci-003 "GPT-3.5" interest and RLHF comes up just about all the time.
Thanks Michael. It's really all moving too fast. I'm trying to maintain this style because I don't write enough for a LLM to capture it anytime soon.
Do you know if there is anyone else at Hugging Face that has a Substack Newsletter? I like the enthusiasm of the LLM movement.
Omar started one recently https://thehackerllama.substack.com/ - He's the lead dev advocate here, so he really knows what's happening.
Thank you, that's super interesting.
This is a really good summary. Really enjoy your writing style. I've been trying to cover the ChatGPT and Davinci-003 "GPT-3.5" interest and RLHF comes up just about all the time.
Thanks Michael. It's really all moving too fast. I'm trying to maintain this style because I don't write enough for a LLM to capture it anytime soon.
Do you know if there is anyone else at Hugging Face that has a Substack Newsletter? I like the enthusiasm of the LLM movement.
Omar started one recently https://thehackerllama.substack.com/ - He's the lead dev advocate here, so he really knows what's happening.
Thank you, that's super interesting.