VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift Paper • 2610.30090 • Published 9 days ago • 12
VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift Paper • 2610.30090 • Published 9 days ago • 12
Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models Paper • 2610.02142 • Published 29 days ago • 6
Running Featured 840 Jev Decision Index 🔬 840 Benchmarks and news on various repros of TypeSafe's Jev
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization Paper • 2610.00906 • Published 29 days ago • 87
Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models Paper • 2610.02142 • Published 29 days ago • 6
jsantillana/vectrayx-vision-1b-qwen-experimental Image-Text-to-Text • 1B • Updated about 1 month ago • 92
jsantillana/vectrayx-vision-1b-qwen-experimental Image-Text-to-Text • 1B • Updated about 1 month ago • 92