Notes
Short posts, notes, and ideas.
-
Human-Written AGENTS.md Still Wins
LLM-generated repo context files can be redundant and even hurt coding-agent performance, while human-written ones are more likely to close the real context gap.
-
Context Learning Is Still Harder Than It Looks
CL-bench shows that frontier models still struggle to genuinely learn and apply novel knowledge that was not part of pre-training.
-
Semantic Layer as Context Infrastructure for Agents
A semantic layer can turn scattered business definitions and local knowledge into explicit context that both humans and agents can use reliably.
-
The Missing Layer in Agent Systems
Explicit context is only part of the problem. The harder part is capturing the reasoning that links information, decisions, and actions.