Mocks, refinement, and what a bug is telling you
Mocks can disappear from an agent’s memory after compaction. Detailed epics help—and bugs remain valuable information about the structure you actually built.
Lynn Cole / Projects
Software, research projects, repositories, and published work.
Mocks can disappear from an agent’s memory after compaction. Detailed epics help—and bugs remain valuable information about the structure you actually built.
A weekend inside an inference engine reveals device middleware, data shaping and old architectural assumptions that still deserve to be challenged.
A Go-native transformer almost works. Tokenizers, vocabulary, norms, cache initialization and attention all take their turn in a night of increasingly interesting nonsense.
Documentation is infrastructure, whether it lives in code, a ticket, a notebook or a coffee-stained napkin. Write down what tomorrow will need.
A range editor needs to know which lines an agent has actually read. My design tracks witnessed content and makes stale edits explicit.
Porting Memvid to Go exposed a chunking problem: six messages can mean wildly different token budgets. A token-aware strategy makes the boundary more predictable.
Prompt moderation is not image moderation. I argue for evaluating generated images and building correction loops around the output.
Bigger embeddings do not automatically mean better retrieval. Match the corpus, chunking, context and search architecture to the job.
A systems breakdown of Salesforce agents: system-prompt load, context saturation, role confusion and the architecture needed for more deliberate workflows.
A satirical ride on the AI hype train, featuring pivot tables, six hundred hello-world nodes and an automatic water-bottle MCP.
A task-completion paper pushes models until they fail. The more revealing part is how confidently people read their own agendas into the result.
Documentation debt is still infrastructure debt. AI makes the habit easier, and information silos remain an expensive way to look busy.