ND “Erdos problem #728 was solved more or less autonomously by AI” (mathstodon.xyz)
619 points by cod1r 58 days ago | 363 comments on HN ~lite vlite-2.0
Summary ~lite
Terence Tao discusses AI solving Erdos problem #728, demonstrating increased AI capability.
Lite evaluation by llama-4-scout-wai-psq · editorial channel only · no per-section breakdown available
Longitudinal · 6 evals
+1 0 −1 HN
Audit Trail 15 entries
2026-03-09 09:21 eval_success PSQ evaluated: g-PSQ=0.320 (3 dims) - -
2026-03-09 09:21 eval Evaluated by llama-4-scout-wai-psq: +0.32 (Moderate positive) 0.00
2026-03-09 09:17 eval_success Lite evaluated: Neutral (0.09) - -
2026-03-09 09:17 eval Evaluated by llama-3.3-70b-wai: +0.09 (Neutral) 0.00
reasoning
Technical math post, no rights discussion
2026-03-09 09:17 rater_validation_warn Lite validation warnings for model llama-3.3-70b-wai: 1W 0R - -
2026-03-09 09:17 eval_success PSQ evaluated: g-PSQ=0.320 (3 dims) - -
2026-03-09 09:17 eval Evaluated by llama-4-scout-wai-psq: +0.32 (Moderate positive)
2026-03-09 09:15 eval_success PSQ evaluated: g-PSQ=0.669 (3 dims) - -
2026-03-09 09:15 eval Evaluated by llama-3.3-70b-wai-psq: +0.67 (Strong positive)
2026-03-09 09:14 eval_success Lite evaluated: Neutral (-0.07) - -
2026-03-09 09:14 eval Evaluated by llama-4-scout-wai: -0.07 (Neutral)
reasoning
Technical discussion on AI solving Erdos problems, no human rights discussion
2026-03-09 09:14 rater_validation_warn Lite validation warnings for model llama-4-scout-wai: 1W 0R - -
2026-03-09 09:12 eval_success Lite evaluated: Neutral (0.09) - -
2026-03-09 09:12 rater_validation_warn Lite validation warnings for model llama-3.3-70b-wai: 1W 0R - -
2026-03-09 09:12 eval Evaluated by llama-3.3-70b-wai: +0.09 (Neutral)
reasoning
Technical math post, no rights discussion