Agents · 1 min · May 16, 2026
Why Agent Reliability Is a Distribution Problem
Single-step accuracy looks fine. Then you chain ten steps and the product falls apart.
Topic
Agents · 1 min · May 16, 2026
Single-step accuracy looks fine. Then you chain ten steps and the product falls apart.
Agents · 1 min · May 10, 2026
Coding agents quietly moved from autocomplete to running the loop. Here is what actually changed, and what it asks of the people who build.
Agents · 1 min · May 10, 2026
The failure mode that matters is not the agent that stops. It is the one that finishes, wrong.
Agents · 1 min · May 3, 2026
Spawning a subagent buys isolation and parallelism. It also fragments context. Pick deliberately.
Agents · 1 min · Apr 25, 2026
Once the prefix is nearly free, the cheap move and the smart move stop being the same thing.
Agents · 1 min · Apr 16, 2026
You would not ship code with no tests. Shipping an agent with no evals is the same bet.
Agents · 1 min · Apr 8, 2026
Most multi-agent systems lose more in the handoffs than they gain from specialization.