All posts
Everything published here, newest first.
317 posts · showing 161–170
2026
10 posts-
The Compounding Loop: Agents Building Agent Infrastructure
Agents are good at building the harness that makes agents useful — well-specified, verifiable plumbing. The loop is real, and it has a hard boundary at everything requiring judgment about what to build.
-
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.
-
Who Adopts First, and Why It Isn't the Biggest Companies
The organizations with the most resources are frequently not the ones deploying furthest. Four things gate adoption, and large companies are structurally worse at three of them — none of which are about technology.
-
What "Agents Got Better" Would Actually Look Like in Your System
Waiting for agents to improve without deciding what improvement looks like makes the waiting unfalsifiable. Write the threshold down first, and every release becomes a measurement instead of a vibe.
-
Why Benchmarks Keep Rising While Deployments Stay Hard
Both reports are accurate. Benchmarks test well-posed, self-contained, checkable problems — and almost none of deployment difficulty is any of those things.
-
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.
-
Longer Context Windows Won't Fix Long-Horizon Tasks
The premise is right — things fall out of context — and the conclusion doesn't follow. Most long-run failures aren't about storage, and a bigger window removes the discipline that was helping.
-
What Gets Cheap Next, and What Stays Expensive
Costs are being rearranged, not reduced. Four things are getting cheap, six aren't — and a fourth category nobody plans for is getting more expensive, including maintaining everything that was cheap to create.
-
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.
-
Debugging Code You Didn't Write and Don't Understand
The instinct is to hand the failure back to the agent. Without a reproduction that produces a plausible fix to a plausible cause — and two rounds later nobody understands the module at all.