GitHub Repository

Two Claude Code skills that run a coding task through a multi-agent harness — plan → N parallel implementations → adversarial verification → judge. pantheon (Claude-only), pantheon-x (GPT-5.5 cross-model verify). MIT.

0 starsJavaScript

AI vs. AI – code and reviews only count if they survive an attack

Name: AI vs. AI – code and reviews only count if they survive an attack
Availability: InStock
Author: lolu1032

by lolu1032·Jun 16, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●MidBold Bet

Adversarial multi-agent verification when best-of-N sampling is already well-documented elsewhere.

Strengths

•Cross-model verification in pantheon-x uses GPT to attack Claude-written code
•pantheon-gap skill applies same harness to review existing projects for gaps

Weaknesses

•Author admits this is scaffolding around models, not novel technique
•Zero stars and forks suggests very early stage with unproven utility

Post Description

Pantheon is a technique for generating each subagent, generating code with different solutions, breaking it and writing code that ultimately survives. For Pantheon-X, GPT 5.5 is broken, and GPT is broken and surviving is the last skill to write code written by Claudette. In the case of Pancheon Gap, it is a technology to continue to check whether the actual review is true and to derive surviving children.

I'd appreciate it if you could actually use it and give me feedback through issues