StampyAI / stampy-chatLinks
Conversational chatbot to answer questions about AI Safety & Alignment based on information retrieved from the Alignment Research Dataset
☆15Updated last week
Alternatives and similar repositories for stampy-chat
Users that are interested in stampy-chat are comparing it to the libraries listed below
Sorting:
- A dataset of alignment research and code to reproduce it☆77Updated 2 years ago
- Drive a browser with Cohere☆72Updated 2 years ago
- Factored Cognition Primer: How to write compositional language model programs☆49Updated 2 years ago
- ☆101Updated 6 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- AI Safety Q&A web frontend☆41Updated this week
- A Loom implementation in Obsidian☆309Updated 5 months ago
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆157Updated 2 years ago
- Interactive Composition Explorer: a debugger for compositional language model programs☆558Updated 2 months ago
- ☆298Updated last year
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆210Updated 3 months ago
- ☆83Updated last year
- A sandbox repo for grounded question answering with Cohere and Google Search☆136Updated 2 years ago
- The history files when recording human interaction while solving ARC tasks☆115Updated this week
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆181Updated 2 months ago
- Tools for studying developmental interpretability in neural networks.☆103Updated 2 months ago
- ☆20Updated last year
- METR Task Standard☆159Updated 7 months ago
- An assistant for betting on prediction markets on manifold.markets, utilizing OpenAI's GPT APIs.☆33Updated last year
- Stampy's copy of Alignment Research Dataset scraper☆13Updated last month
- Command-line recursive question-answering with immutable contexts and explicit data store☆26Updated 6 years ago
- ☆17Updated last week
- ☆18Updated 2 years ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆110Updated this week
- Erasing concepts from neural representations with provable guarantees☆233Updated 7 months ago
- Experimental LLM interface exploring new ways to use AI to improve human thinking☆19Updated 6 months ago
- Used for adaptive human in the loop evaluation of language and embedding models.☆311Updated 2 years ago
- ☆138Updated last month
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated 2 years ago
- ☆26Updated 3 months ago