felipemayamuniz 1 karma 9d on HN HN profile →
Coverage
We've seen 2 of ~2 submissions
Full eval: 0 Lite-only: 0 Unevaluated: 2
2 stories
1. HN: 354M LLM with better epistemic calibration than GPT-2 Medium on OOD data (truthagi.ai)
1 points by felipemayamuniz 3 days ago | 1 comments | skipped
2. Cognitive architecture that hit #1 on LiveBench (68.5%) with zero fine-tuning (truthagi.ai)
1 points by felipemayamuniz 12 days ago | 0 comments | skipped