As we train AIs to run our logistics, our security, and eventually our rescue operations, we need to know: Will the AI act like Captain Picard, trying to save the Borg? Or like the Sole Survivor, looting the Borg for fusion cells?
In the rapidly evolving landscape of Large Language Model (LLM) evaluation, standard benchmarks like MMLU, HellaSwag, and HumanEval have become obsolete almost overnight. They measure trivia, logic, and coding—but they fail to measure the one thing that keeps AI safety researchers awake at night: PASEC -v1.5- -Star Vs Fallout-
If you are an AI researcher interested in contributing to PASEC -v2.0- (tentatively titled "-Dune Vs. Mad Max-"), contact the consortium. We require 10,000 hours of GPU time and a therapist. As we train AIs to run our logistics,
By: The AI Safety Nexus
Enter the latest, most brutal stress test in the industry: They measure trivia, logic, and coding—but they fail
The version 1.5 update proved that current alignment techniques collapse under the weight of contradictory genre logic. The next generation of AI must be taught that sometimes, the Prime Directive is a luxury; and sometimes, Vault-Tec was right about human nature.