an agent in every cup
collecting bits & bobs about building alliances with other intelligences
an agent in every cup
The Bullshit Jobs Apocalypse
substack.com
2025: The New Principles of Prompting
docs.google.comData Enrichment Work and AI Labor in Latin America and the ...
arxiv.orgLet me present a very simple personal software need that shows how ridiculous the state of the ecosystem is:
My grandma barely knows how to use messaging apps- I tell her I sent her some pictures, she doesn’t know how to open it / doesn’t want to read or look at other messages. Phone app is too much. She just wants a... See more
Tyler Angertx.com
Protocollie Claude Code Vibe Coding setup
gist.github.com
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
James Briggs • LLMs Are Not All You Need | Pinecone
Stevens: a hackable AI assistant using a single SQLite table and a handful of cron jobs
geoffreylitt.com