August 29, 2026
AutoHarness: What If Claude Code Could Learn From Your Real Work?
The model matters. But the harness around it can matter just as much.
Insights
Page 2
August 28, 2026
From Quote to Coverage: How AI Is Changing the Insurance Buying Journey
Most digital insurance projects of the last decade moved offline processes online without changing them. The forms got fillable; the friction stayed. What AI makes possible is different, and it is worth being specific about where in the purchase it actually lands. This piece follows one journey end to end: understanding, quoting, applying, waiting, being told the answer, and being covered. Each step has a different failure mode and a different regulatory ceiling.
August 28, 2026
I Found A Free GitHub Plugin That Took Claude Code CORE-Bench Score From 42% to 78%
Let me tell you a small problem I kept running into. I use Claude Code almost every day for coding work. And every few days, I found myself typing the same correction again. "No, we use pytest here, not unittest." I had already told it this before. But it forgot. This happened again and again. Small thing, but when it happens 30 times a month, it stops feeling small. Then I came across a plugin called autoharness. And it fixed this one exact problem for me. Let me explain it in the simplest way I can.
August 27, 2026
Tigerless Labs AutoHarness: Why the Same AI Model Can Score 42% or 78% Depending on Its Harness
There is a benchmark result that should make every AI power user stop and re-read it: the same underlying model, run against the same set of tasks, scores 42% under one configuration and 78% under another — a result measured on CORE-Bench inside the HAL benchmark (arXiv:2510.11977). Not a different model.
August 24, 2026
AI in Insurance Pricing: Bias, Fairness, and Regulation
Artificial intelligence is changing insurance pricing, but the hardest question is not whether algorithms should charge everyone the same price. Insurance has always depended on telling different levels of risk apart. The real challenge is deciding when technology identifies legitimate, lawful differences in risk, and when the data, proxy variables, or model design produce differences nobody can justify.
August 17, 2026
Can AI Explain Your EOB? A Simple Guide to Health Insurance EOBs
Confused by your health insurance EOB? Learn what billed charges, allowed amounts, deductibles, and patient responsibility mean, and how AI can help.