LegalRealist AI

The APEX benchmark — built by Mercor, with tasks authored by BigLaw-experienced lawyers and advised by Cass Sunstein — is the most rigorous test of whether AI can perform real legal work. The answer is more specific than vendors or skeptics suggest.

An Instagram account-takeover wave exploited Meta's AI support bot at the password-reset gate. The lesson for law firms: authentication and ethical walls exist to refuse persuasion — exactly what agents are built to do well.

Excel custom number formats let a cell store one value and display another. Every extraction library reads the stored value. Every LLM platform I tested shifted from 'do not pursue' to qualified interest on the same file.

Every headline called Kirkland's $500M commitment an AI bet. The signals in the announcement — no named model, full exclusivity, value-based pricing — point to something different: an infrastructure play that happens to run AI.

AI processing costs ~3% of an AI-enhanced eDiscovery workflow. The real savings come from restructuring leverage — shifting volume QC from $750/hr associates to $50/hr contract attorneys. Here's the math.

A walkthrough of building a Medicare fraud backtest overnight in Claude Code — from a plain-English spec to 289 matched providers across 41 states, a predictive model with AUC 0.79, and out-of-sample validation. Including the three times the pipeline failed, the data duplication bug, and the engineering decisions that shaped the final design.

The attack surface isn't AI — it's the documents AI processes. Prompt injection in discovery, adversarial inputs delivered through Rule 34 productions, and the cybersecurity gaps firms create by piping untrusted content through LLM pipelines.

The previous post described a Medicare fraud backtest nobody had built. I built it. 289 excluded providers across 41 states, matched to pre-exclusion billing data, compared against 3.39 million peers. Thirteen of fifteen features showed statistically significant differences — and the behavioral fingerprint is consistent enough to predict fraud in providers who were never excluded.

How we merged two overlapping court order trackers, enriched missing fields with Claude Haiku for a few cents, replaced 200 paywalled links with free CourtListener alternatives, and shipped a searchable explorer — all through conversational prompting with Claude Code.

Both leading AI court order trackers merged into a free, searchable explorer — 643 orders, organized by judge, with paywalled links replaced.