Development

A competitive security format breaks as scores track token budgets

development2026-05-17

Claim

GPT-5.5 Pro one-shots challenges rated insane in open capture-the-flag competitions, and the scoreboard now reflects token budgets rather than human skill.

Reporting date: 2026-05-17 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to May 17, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to May 17, 2026

Actor

OpenAI

Evidence for

Supersedes

Defenders are given a three-to-five-month window to harden systems

Referenced by

Cite or correct this record

Citation formatCitation text

A competitive security format breaks as scores track token budgets
Innermost Loop KB — secondary record
Reporting date: 2026-05-17
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-05-17-the-scoreboard-reflects-token-budgets
Claim: GPT-5.5 Pro one-shots challenges rated insane in open capture-the-flag competitions, and the scoreboard now reflects token budgets rather than human skill.
Attributed sources:
- Welcome to May 17, 2026 — https://theinnermostloop.substack.com/p/welcome-to-may-17-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.