Why 10 million tokens is the only memory benchmark that matters
Apr 2, 2026
Hindsight is #1 on BEAM at the 10M token tier. At that scale, context-stuffing dies and only real memory architecture survives.
That's not how you do business
Mar 24, 2026
Supermemory gamed a memory benchmark for viral reach, then called it a social experiment. Why stunts erode trust and what real benchmarking looks like.
Open source is a trust system. AI is breaking the contract.
Mar 16, 2026
AI lets people contribute to open source without understanding what they change. The OSS trust model needs human attestation, not just AI disclosure.
Not all agents are the same: task agents vs interaction agents
Mar 4, 2026
Task agents and interaction agents need different memory stacks. Latency, retrieval quality, and error tolerance diverge in ways most frameworks ignore.
AI won't replace engineers, it will replace project managers
Feb 28, 2026
AI coding agents eliminate the translation layer between users and code - the exact role PMs fill. Engineers who own the full product loop will thrive.
