Press Space to continue
Curated tech posts from X on AI, startups, and product development—signal without the doomscroll, updated on weekdays.
Press Space to continue
Press Space to continue
i had codex benchmark a competitor and their p50 is 400ms lol once executor supports public apps i'll make the latency dashboard public
p50 latency executor adds to tool calls is now down to ~45 ms still above my goal of 10ms, but i have some future plans of how this'll actually end up being faster than calling an MCP directly from your harness with batch endpoints and dynamic placement
