#advanced
Every post tagged "advanced".
48 posts · showing 11–20
-
Designing an Agent You Can Redirect Mid-Run
Twelve files into forty, you realize the approach is wrong. Let it finish or kill it — both bad, and the third option had to be designed in before the run started.
-
Three Ways to Get Valid JSON, and What Each One Costs
The retry loop was working and quietly biased: the tickets needing three attempts weren't a random sample, and their eventual valid output was thinner than the truth.
-
Your Trace Store Will Outgrow Your Model Bill
Storage passed inference cost in three weeks, and the proposed fix — sample at 5% — would have discarded exactly the runs worth keeping. A trace isn't one artifact with one lifetime.
-
Budgeting the Context Window: Dividing a Fixed Space
The window wasn't full and the constraints still vanished — because six claimants compete for one space and nobody allocated it. Making history the residual rather than a claimant is what makes the scheme work.
-
Compliance and Audit for Agent-Written Systems
The audit questions don't change — who's responsible, how do you know it's correct, show me this case. They become answerable differently, and an actor field saying "agent-service" answers the first one not at all.
-
What Distributed-Systems Experience Transfers to Agent Loops
An agent run is a distributed system with unreliable participants, so most of the discipline transfers. Four things twist — and one microservice instinct actively hurts, because agent boundaries are lossy.
-
The Loop Decisions You Only Make Once
Most agent design choices are cheap to revise. Six aren't — and in every case the answer that ages well is the same one, for the same reason.
-
What Happens When Verification Gets Automated Too
"Agents generate, humans verify" is stable partly because verification is hard to automate. Parts of it aren't — and the part that survives isn't reviewing, it's knowing what was wanted.
-
The Reliability Ceiling and What Would Have to Change
98% per step sounds excellent and produces 67% on a twenty-step task. The plateau is compounding arithmetic — which means the fix is shortening the chain, not improving the steps.
-
Predicting Agent Capability: Reason From Mechanism, Not Vibes
"Will agents get better?" is the wrong question. Six things block any given task, only two of them move with model releases — and the other four are the ones nobody's working on.