In my last post, I laid out the core inequality of Speculative Decoding: a > 1 + α +...
I Benchmarked Speculative Decoding — a = 3.5 Wasn't Enough
Related
OKF for Claude Code: structured, portable memory your agent (and team) can read
The problem: agents forget your project every session If you pair with a coding agent, you...
Stop Asking the LLM Whether Its Source Is Real
An LLM invents plausible citations then confirms they're real. The only fix: resolve every source against an external API. A three-filter pipeline.
No Agent Grades Its Own Homework
An LLM reviewing its own code over-rates it: a measured bias. Blind reviewer, finding with a receipt, refute panel: the architecture of an AI review that holds.