Tool descriptions need continuity across loops
A curated tool list is only the start. Agents also need discovery and project notes that carry tool instructions into the next loop.
Lynn Cole / Writing
Writing
Essays, thoughts, and technical notes.
What behaviors are you rewarding in an agent?
What behavior does your agent’s reward system encourage? Composite goals and visible progress can keep the game aligned with the actual work.
When a model calls the task chaotic
When a model calls a task chaotic, it may be recognizing a different kind of signal. I explore that response through Dada, metaphor and primordial chaos.
A working taxonomy of hallucination failures
A working taxonomy of hallucination failures, centered on alignment, reward signals, role separation and the software around the model.
Intuition, automatism, and anti-process
Intuition, automatic writing and divided attention lead me toward an anti-process: art that laughs at its own attempt to destroy meaning.
Choosing a first language for modern engineering
Choosing a first language means thinking about syntax, transferable skills, setup, longevity and the culture of its community.
Vibe coding and the upstream work of quality
Vibe coding moves more of quality upstream into requirements, prompts and validation, while giving more people a way to try building.
Why do we keep getting context windows wrong?
Where do we even begin with LLaMA 4 Scout and the promise of an “effectively unlimited” context window?
Unstated architecture is still a developer’s responsibility
Architecture that remains unstated is still the developer’s responsibility. Models, prompts, frameworks and modular design all need deliberate choices.
Context capacity does not remove complexity limits
Large context capacity does not remove complexity limits. Scope, memory, smaller components and clear boundaries still matter.
The old engineering work inside the new workflow
The familiar engineering work—planning, patterns and review—still lives inside the new AI coding workflow.
Why this is more than another Tuesday
AI is an opportunity to rethink workflows, not merely add another layer to broken ones. Ask why the system exists before streamlining it.