Telling an LLM to 'be creative' is one of the worst things you can do
What Arthur Koestler's bisociation theory suggests, and how I ported the Open-Collider method into a Hermes skill.
Articles about "ai".
What Arthur Koestler's bisociation theory suggests, and how I ported the Open-Collider method into a Hermes skill.
A concrete integration bug from an AI-built research system: both sides of a contract had passing unit tests, but the real components broke when they met.
What changed when checkpoint gates stopped being just approval steps and became the place where the architecture improved.
Why I wrote a full spec pack before building an autonomous European equities research system with an AI agent, and why the docs were useful precisely because they were allowed to change.
A European equity research pipeline built around audit trails, backtests, refusal points, and a dashboard that exposes what the agents did instead of hiding it.