an agent in every cup

an agent in every cup

collecting bits & bobs about building alliances with other intelligences

GitHub - microsoft/TinyTroupe: LLM-powered multiagent persona simulation for imagination enhancement and business insights.

Thumbnail of GitHub - microsoft/TinyTroupe: LLM-powered multiagent persona simulation for imagination enhancement and business insights.

Think First, AI Second

Ines Lee every.to

Thumbnail of Think First, AI Second

Home-Cooked Software and Barefoot Developers

Maggie Appleton maggieappleton.com

Thumbnail of Home-Cooked Software and Barefoot Developers

Is it okay?

Robin Sloan robinsloan.com

Thumbnail of Is it okay?

SpeedReader/.claude/skills/skill-creator/SKILL.md at main · j-r-beckett/SpeedReader

Thumbnail of SpeedReader/.claude/skills/skill-creator/SKILL.md at main · j-r-beckett/SpeedReader

We had an AI attempt to make a data-driven story like we do at The Pudding

Claude 3 pudding.cool

Thumbnail of We had an AI attempt to make a data-driven story like we do at The Pudding

🎧 How to Use Claude Code as a Second Brain

GitHub - huggingface/smolagents: 🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

Thumbnail of GitHub - huggingface/smolagents: 🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

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

... See more

James Briggs • LLMs Are Not All You Need | Pinecone