When harnesses compact conversations, skills fade.
Worse: echoes of their existence actively harm subsequent recall.
It turns out harness compaction choices and skill loading instructions combined make or break whether skills are lost or refreshed.
https://t.co/BYMMqCBouO
@KeithZhai@Paul_Kinlan The semi-fixed wait time that's only forcefully terminated at process exit
Humans can consume incrementally, but agents cannot (based on the harnesses that are controlling them).
Your AI coding agent isn't slowed down by inference time alone, but by harness assumptions that treat process exit as the prerequisite for tool output consumption
In https://t.co/WFWGrPvNCq I explore Time to Awareness (TTA) and a path forward to unblock harnesses running human-centric CLIs to accelerate the agent iteration loop.
@sujiteeeey Agreed, my meta point though is that actionable data can be emitted prior to done, and right now all the harnesses more or less simply ignore this fact
Work no longer being proof of work is reshaping what it means to learn and what is value.
Verbiage around "slop" fundamentally stems from the new divide - The work to verify now often greatly exceeds the work to produce.
What once was a teaching moment becomes a meat proxy experience.