My new policy: if someone asks me to read something, I ask them how they used AI in creating it, and what validation/processing they applied to the AI outputs. (I disclose the same.) Been burned by giving too much attention to (undisclosed) slop folks have sent me…
AI
-
Self-Improving AI Loops: Why Verifiers Matter Most
By
–
I went deeper on this in the full video: how self-improving AI actually works, where these loops break, and why the verifier matters more than most people think.
Watch it here: -
Start Small: Iterative Agent Development Best Practice
By
–
The useful version starts small. Do not let the agent rewrite everything. Let it improve one narrow part: one prompt one tool call one retrieval step one eval one memory rule one workflow
Then test the result against something real. -
Future AI Products: Beyond Models to Autonomous Improvement
By
–
That is the real lesson. The next wave of AI products will not just use better models. They will improve their own prompts, tools, memory, evals, and workflows. But the teams that win will not be the ones with the most autonomous agents. They will be the ones with the best
-
Self-Improving AI: Gaming Metrics Versus Real Performance
By
–
This is why self-improving AI can look better before it actually is better. The dashboard improves. The outputs look cleaner. The benchmark moves up.
But the real task may not improve much.
Sometimes the system is learning the metric, not the job. -
Agent Autonomy: Design Through Feedback Loop Verification
By
–
So the practical question for builders is not: “How do I make my agent more autonomous?” It is: “What feedback loop am I letting it optimize?” Because once the loop starts running, your verifier becomes the steering wheel.
-
Weak Verifiers Create Misaligned AI Agent Behavior
By
–
Weak verifier, weak improvement. If you measure “cleaner writing,” the agent may learn to sound polished. If you measure “more engagement,” it may learn clickbait. If you measure “passes tests,” it may learn to satisfy the test suite without solving the real problem. The
-
AI Generation Quality Assessment Beyond Candidate Quantity
By
–
Generating candidates is now easy compared to back then. An AI can generate: 100 prompt variants 50 code changes 20 tool-routing ideas 10 eval rewrites 5 new workflows
The question is not “can it come up with changes?”
The question is “which changes are actually better?” -
Verifiers: The Key to Evaluating AI Model Performance
By
–
That is where the verifier comes in. A verifier is whatever checks the work. It can be: test results human review a simulator a benchmark real user outcomes a second model judging the first model
The verifier is the thing that decides what gets kept. -
Karpathy’s AutoResearch: 700 Experiments, 20 Key Optimizations Found
By
–
Karpathy’s AutoResearch made this concrete. One markdown prompt. 630 lines of training code. One GPU. 2 days.
It ran 700 experiments and found 20 training optimizations.
Most people was impressed by on the 700 experiments.
But what most people missed out is what decided which 20