ND Why deep learning works even though it shouldn’t (moultano.wordpress.com)
356 points by r4um 1972 days ago | 142 comments on HN ~lite vlite-2.0
Summary ~lite
Blog post on deep learning with neutral tone and author identified.
Lite evaluation by llama-4-scout-wai-psq · editorial channel only · no per-section breakdown available
Longitudinal · 5 evals
+1 0 −1 HN
Audit Trail 10 entries
2026-03-05 17:39 eval_success PSQ evaluated: g-PSQ=0.280 (3 dims) - -
2026-03-05 17:39 eval Evaluated by llama-4-scout-wai-psq: +0.28 (Mild positive)
2026-03-05 17:38 eval_success PSQ evaluated: g-PSQ=0.198 (3 dims) - -
2026-03-05 17:38 eval Evaluated by llama-3.3-70b-wai-psq: +0.20 (Mild positive) 0.00
2026-03-05 17:34 eval_success PSQ evaluated: g-PSQ=0.198 (3 dims) - -
2026-03-05 17:34 eval Evaluated by llama-3.3-70b-wai-psq: +0.20 (Mild positive)
2026-03-01 22:45 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-01 22:45 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral)
reasoning
Technical article on deep learning, no human rights discussion
2026-03-01 22:43 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-01 22:43 eval Evaluated by llama-3.3-70b-wai: 0.00 (Neutral)
reasoning
Tech blog no rights stance