Skip to the card

Card 279 of 9912026-09-15 issue

Observed arrival · 2026-09-15

ExplorationBench Makes AI Explore Alien Rules

explorationbench.com Observed source
Editorial interest 86/100 Selection signal · not a rating of the site

An open benchmark tests whether AI systems can discover hidden semantics in executable worlds rather than rely on memorized knowledge.

Landing page captured for the 2026-09-15 issue.

Field notes

ExplorationBench separates discovering a rule from merely recalling a familiar domain. AlienCode tests programs against private inputs through an interpreter, while AlienLogic checks Fitch-style proofs and includes 21 unprovable goals where refusal can be correct. Its protocol compares four rounds of probing across twenty system–sandbox pairs, with each leaderboard cell averaged over three runs.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

OpenPublic substance visible
PrettyNotable craft visible
ProPolished or operationally mature
NicheUnusually specific use

One card from the complete issue

Pepperoni in a Rearranged Kitchen

395,658 arrived 1,000 judged 991 catalogued Enter the complete issue
explorationbench.com

Landing page observed 2026-09-15. The live site may have changed.