atticusw

Karma: 15

[CS2881r] Optimizing Prompts with Reinforcement Learning

Anastasia Ahani and atticusw

1 Oct 2025 14:02 UTC

2 points

0 comments5 min readLW link

[CS 2881r AI Safety] [Week 1] Introduction

bira, nsiwek and atticusw

14 Sep 2025 19:52 UTC

15 points

0 comments13 min readLW link

atticusw 23 Mar 2025 19:05 UTC
2 points
0
on: Logits, log-odds, and loss for parallel circuits
What is the formal statement of the fact that logits add for perfectly calibrated and maximally independent predictions?