HN Explorer

shubh-chat

↗ HN profile [ 21.9 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: LOAB – AI agents get decisions right but skip the process [pdf] (github.com)

    LOAB, an open-source benchmark for evaluating whether AI agents can follow regulated lending processes — not just produce the right final answer. The motivation is simple: in mortgage lending, regulators don't care if…

    1 points 0
  2. Show HN: LOAB – benchmarking AI process fidelity in lending (github.com)

    As the conversation around AI replacing knowledge work gets louder, I wanted to test it against something actually messy — a real lending workflow with regulations, ordered steps, and hard policy constraints. LOAB is my…

    1 points 0