2026-06-28
The industry is building a staircase to nowhere, while true intelligence requires a foundation.
A critique of agent-centric AI architecture and an argument for c = a + b foundations built around Memory Gate, witness dependency, and resource accountability.
2026-04-09
That is why this package does not stop at concepts.
A note that the first honest implementation slice is a bounded chain from runtime collision to quarantined research, not a larger agent demo.
2026-04-08
I also published a graph / visibility layer for the L4 glitch stack.
A note that visibility layers should make branches legible without turning displayed possibilities into runtime authority.
2026-04-07
One of the most dangerous habits in current AI systems is this:
A note that runtime boundaries should be treated as structural events, not smoothed over with fluent continuation.
2026-04-04
A serious system does not improvise through failure. It stops.
A note that serious AI systems should stop at real boundaries, record collisions, quarantine blocked futures, and keep visibility separate from authority.