an agent in every cup

collecting bits & bobs about building alliances with other intelligences

"I don't use RAG, I just retrieve documents"

Generative AI and Labor

People assume that generative AI will lead to a tsunami of garbage content. I think the opposite problem is more interesting: what if you were drowning in amazing content? What if you’re so inspired and overwhelmed by awe that it’s stressful and addicting and life disorienting?

DeckFlow: Iterative Specification on a Multimodal Generative Canvas

arxiv.org

GitHub - m-damien/Textoshop: 📝 An intelligent text editor with interactions inspired by drawing software

github.com

Extending AI chat with Model Context Protocol (and why it matters)

interconnected.org

Prompt Engineering

kaggle.com

🎧 How to Use Claude Code as a Second Brain

every.to

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