an agent in every cup

collecting bits & bobs about building alliances with other intelligences

kaiton

Malleable software: Restoring user agency in a world of locked-down apps

Geoffrey Litt inkandswitch.com

All AI Models Might Be The Same

blog.jxmo.io

Eureka Labs

eurekalabs.ai

Mirror, mirror… what we often misinterpret when we talk about large language models. Source: Betley, Tan, Warncke et al, “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs”: emergent-misalignment.com #ai #llm #gpt #claude #artificialintelligence... See more

tiktok.com

How We Built Our Multi-Agent Research System

anthropic.com anthropic.com

True Agentic RAG: How I Taught Claude to Talk to My PDFs using Model Context Protocol (MCP)

Alexander Komyagin medium.com

OpenAI Has Some Catching Up to Do

Dan Shipper every.to

GenAI is Our Polyester

culture.ghost.io

Programming as Theory Building

Peter Naur's "Programming as Theory Building" discusses programming as a knowledge-building activity, emphasizing the importance of tacit knowledge, collaboration, and effective documentation in developing and maintaining software systems.

ratfactor.com