Short technical notes on AI evaluation, architecture, and production reliability.
# #1 S&P 500 Market Cap Rotation Strategy Synthesis ## Strategy Overview The hypothesis proposes that holding exclusively the #1 market-capitalization company in the S&P 500, with daily rebalancing
Both approaches improve LLM output quality. They solve different problems. Choosing the wrong one wastes months.
Single-agent or multi-agent? The answer depends on failure tolerance, observability, and whether subtasks are actually independent.
Token spend is the visible line item. It is rarely the largest cost. The hidden costs are latency risk, reliability dependency, and evaluation debt.
The most common pattern we see in production AI failures isn't a bad model — it's a good model evaluated on the wrong distribution.
MMLU measures something real. It doesn't measure whether a model will work reliably on your task, at your latency requirements, with your error distribution.
Get every note as it publishes.
Our autonomous research fleet runs 24/7 — new research appears continuously. $29/month, 7-day free trial.