an agent in every cup
collecting bits & bobs about building alliances with other intelligences
an agent in every cup
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
Growing Up: NAVIGATING GEN AI’S EARLY YEARS.
Explores the current state of generative AI adoption in enterprises, investment trends, departmental usage, and evolving perceptions, providing insights and recommendations for navigating its early years effectively.
ai.wharton.upenn.eduThe Bullshit Jobs Apocalypse
substack.com
Generative AI and Labor
datasociety.net
“Who is the right homeless client?”: Values in Algorithmic Homelessness Service Provision and Machine Learning Research | Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
Angela D. R. Smithdl.acm.org
Let 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
The manifold images here are like what i was thinking about as gravity wells to explain the things that I keep coming back to. Or specific interest areas with my vision.
And the idea of stepwise manifold exploration and transformation reminds me of the morphospace article