Six months ago I set out to make LLMs "smarter" by orchestrating many of them together. I measured...
Six months ago I set out to make LLMs "smarter" by orchestrating many of them
together. I measured it. It didn't work. Here's what I shipped instead — and why
the failure is the part I'm proudest of.
The idea that failed (and why I'm telling you)
The plan was "mitosis": split a task across several LLMs, let them multiply and
I didn’t set out to write a benchmark paper. I wanted to answer a much dumber, much more practical...
How a portfolio-monitoring bot taught me how LLMs really work: zero-temperature non-determinism, determinism in the data, and…
10 adversarial scenarios, 64 assertions, 3-tier evaluation pyramid. Llama, Qwen, GPT-OSS — none scored above 63%. Here's what…
A few months ago, I shipped my first "production-ready" AI application. It worked beautifully — right...
I tried to build a SaaS. I'm shipping tiny libraries instead. For 7 days I poured energy...
As context windows grow, LLM performance degrades in unexpected ways. We show how a "Divide & Conquer" framework — breaking long…
