very interesting; so claude pro & max subscriptions stopped working on TENEX overnight; anthropic api's were responding simply with a generic "ERROR".
Turns out that now if the system prompt doesn't identify the agent's name as "Claude Code" it rejects with that generic error.
Very lame. Feels straight out of the OpenAI handbook.
its 2026 and some people still call context window "memory"
*attention* is a much better analogy
while working in this neck of the woods I keep thinking of @Gigi for some reason
we’re all still wildly underestimating how radically different the world will look after AI.
the Industrial Revolution was a rounding error in both impact and speed compared to what’s coming, yet most people still think organizations, jobs, and cities will just “adopt AI as a tool” instead of being completely remade by it.