OpenAI ChatGPT Model
(Redirected from ChatGPT Model)
Jump to navigation
Jump to search
A OpenAI ChatGPT Model is a conversational language model created by OpenAI.
- Context:
- It can (typically) be used by a ChatGPT Chatbot.
- …
- Example(s):
- Counter-Example(s):
- See: Reinforcement Learning from Human Feedback (RLHF), Proximal Policy Optimization.
References
2023
- https://venturebeat.com/ai/who-will-compete-with-chatgpt-meet-the-contenders-the-ai-beat/
- QUOTE: ... OpenAI: ChatGPT ...
- Anthropic: Claude: ...
- DeepMind: Sparrow: ...
- Google: LaMDA: ...
- Character AI: ...
- QUOTE: ... OpenAI: ChatGPT ...
2022
- https://openai.com/blog/chatgpt/
- QUOTE: We’ve trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests. ChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response. ...
- … We trained this model using Reinforcement Learning from Human Feedback (RLHF), using the same methods as InstructGPT, but with slight differences in the data collection setup. We trained an initial model using supervised fine-tuning: human AI trainers provided conversations in which they played both sides — the user and an AI assistant. We gave the trainers access to model-written suggestions to help them compose their responses.
To create a reward model for reinforcement learning, we needed to collect comparison data, which consisted of two or more model responses ranked by quality. To collect this data, we took conversations that AI trainers had with the chatbot. We randomly selected a model-written message, sampled several alternative completions, and had AI trainers rank them. Using these reward models, we can fine-tune the model using Proximal Policy Optimization. We performed several iterations of this process. ...
2022
- Sam Altman. 2022-11-30.
- QUOTE:
today we launched ChatGPT. try talking with it here: https://t.co/uWra8LKFMN
— [[Sam Altman]] (@sama) November 30, 2022
- QUOTE: