an agent in every cup
collecting bits & bobs about building alliances with other intelligences
an agent in every cup
Sign in - Google Accounts
aistudio.google.comGitHub - JeredBlu/custom-instructions
github.comGitHub - OSU-NLP-Group/HippoRAG: [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs +...
github.com![Thumbnail of GitHub - OSU-NLP-Group/HippoRAG: [NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs +...](https://s3.amazonaws.com/sublimeinternet-public-storage-production/media/images/thumbnails/curation/cc536e2f/thumbnail.png)
GitHub - circlemind-ai/fast-graphrag: RAG that intelligently adapts to your use case, data, and queries
Charles Dickensgithub.com
Effectiveness of Mastery Learning Programs: A Meta-Analysis
The article presents a meta-analysis of mastery learning programs, evaluating their effectiveness in improving student learning outcomes and academic performance compared to traditional instructional methods.
uky.eduAI is aggregated human intelligence. So it’s better to call it collective intelligence than artificial intelligence.
Emphasizing the collectivity (something built on the commons) over the artificiality (a feat of technology) gives us an entire new way to see, perceive and relate to the technology.
-via Holly Herndon, in conversation with Ezra Klein
Indeed, AI is a diffuse term that corresponds to a web of human actors and computational processes interacting in complex ways
Sydney Levine • Who gets credit for AI-generated art? – MIT Media Lab
An agent can be thought of as a logical wrapper around an LLM, allowing us to add several features to our AI systems, primarily:
- Tool usage, such as calling APIs for info, executing code,
- Internal thoughts over multiple generation steps
- Ability to use various tools and reasoning steps to answer more complex queries.
- Parallel agents can go and complete