AI Giants Go Nuclear, A Tech Bromance Turns Turbulent, Mistral Sharpens the Edge, and more...#Startups#Feedback#Prototype#Generative AI#Blog·deeplearning.ai·Oct 29, 2024AI Giants Go Nuclear, A Tech Bromance Turns Turbulent, Mistral Sharpens the Edge, and more...
Suppressing Pink Elephants with Direct Principle FeedbackDownload PDF#Large Language Models#Feedback#Paper#PDF·arxiv.org·Feb 13, 2024Suppressing Pink Elephants with Direct Principle Feedback
Direct Preference Optimization: Your Language Model is Secretly a Reward Model | DPO paper explained#Fine-Tuning#Large Language Models#Feedback·youtube.com·Dec 26, 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Model | DPO paper explained
The third New England RLHF Hackers Hackathon#EleutherAI#Event#Reinforcement Learning#Feedback·blog.eleuther.ai·Nov 26, 2023The third New England RLHF Hackers Hackathon
Scientists Are Researching a Device That Can Induce Lucid Dreams on Demand#Brain Science#Feedback·vice.com·Nov 5, 2023Scientists Are Researching a Device That Can Induce Lucid Dreams on Demand
Yann LeCun on X#Opensource#Feedback#Platforms#Large Language Models·twitter.com·Oct 16, 2023Yann LeCun on X
Human Feedback is not Gold StandardDownload PDF#Large Language Models#Feedback#Criticism#RLHF#Paper#PDF·arxiv.org·Oct 4, 2023Human Feedback is not Gold Standard
OpenELM/OpenELM_Paper.pdf at paper · CarperAI/OpenELM · GitHub#Large Language Models#Algorithms#Feedback#Paper#PDF·github.com·Jul 11, 2023OpenELM/OpenELM_Paper.pdf at paper · CarperAI/OpenELM · GitHub
SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation#Large Language Models#Feedback·kaistai.github.io·Jun 5, 2023SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation
Quicker feedback on new content#Quora#Feedback·productupdates.quora.com·Mar 16, 2023Quicker feedback on new content
Addressing criticism, OpenAI will no longer use customer data to train its models by default#OpenAI#Privacy#Feedback#RLHF·techcrunch.com·Mar 1, 2023Addressing criticism, OpenAI will no longer use customer data to train its models by default
The Flan Collection: Advancing open source methods for instruction tuning#Instruction#Machine Learning#Fine-Tuning#Prompt Engineering#Research#Google#Opensource#Feedback·ai.googleblog.com·Feb 2, 2023The Flan Collection: Advancing open source methods for instruction tuning
Charlie George on Twitter#Elicit.org#Feedback#Abstract#Large Language Models·twitter.com·Jan 21, 2023Charlie George on Twitter