Here are the entrants for the "Chat-Your-Data" Challenge. Check them out for great examples of "ChatGPT over your data" Reminder, whichever repo has the most stars after a week wins! So go star the repos you like best Blog Post: https://
blog.langchain.dev/chat-your-data
-submissions/
… Entrants below
AGENTS
-
Chat-Your-Data Challenge: Best ChatGPT Data Integration Solutions
By
–
-
Survey on Transformers Applications in Reinforcement Learning
By
–
A Survey on Transformers in Reinforcement Learning Transformers have been the prime mover of almost all modalities, from vision, speech, text and are showing potential applications in RL. This survey paper provides a nice taxonomy of Transformers in RL. https://
arxiv.org/abs/2301.03044 -
Content-Conditioned Q&A Assistants: A Future Feature
By
–
content-conditioned Q&A assistant is a prominent feature of the future.
-
ChatGPT Replaces StackOverflow for Instant Technical Solutions
By
–
Say goodbye to endless scrolling on StackOverflow!
— Shubham Saboo (@Saboo_Shubham_) 12 février 2023
Get instant answers from ChatGPT, the ultimate tech problem solver.
pic.twitter.com/oX2mfijRO8Say goodbye to endless scrolling on StackOverflow! Get instant answers from ChatGPT, the ultimate tech problem solver.
-
Learning from Preferences: RLHF, Policy Gradients, and Dagger
By
–
Finally, when learning from preferences, one learns an F(x,y) that enables one to rank and select or do policy gradients (e.g. PPO) as in most RLHF. When the interface allows for corrections (e.g. rewriting the response in a chat agent), then we are in the domain of Dagger.
-
Dagger Imitation Learning: Human Feedback for Agent Training
By
–
Imitation with Dagger: In counterfactual learning F is typically the identity. The agent acting with policy p(y|x) determines the x’s as in RL, but humans (or other agents) provide corrections in the form of y’s. The new data is used for retraining.
-
Self-Training: Filtering Functions and Model Ranking Systems
By
–
Self-training: F(x,y) is a filtering/ranking function, eg., what we call a reward/return. The input x may be chosen by humans, but the model generates the y’s and F ranks and selects for further rounds of self-training. F can be explicit or implicit (human in the loop as in RLHF)
-
ChatGPT vs Bing: Basic Riddle Performance Analysis
By
–
Acertijos básicos: ChatGPT mal, y Open Bing bien… pero en realidad no.
-
CICERO by Meta AI: Strategic Dialogue Generation Process
By
–
#CICERObyMetaAI generates strategic, free-form dialogue by: Predicting the moves other players are likely to make. Creating a plan based on those predictions. Generating messages. Filtering the final messages for clarity and value. Read more on our blog
