Model Comparison
Model Editorial Structural Class Conf SETL Theme
@cf/meta/llama-4-scout-17b-16e-instruct lite ND ND — 0.70 — —
@cf/meta/llama-4-scout-17b-16e-instruct lite +0.40 +0.17 Moderate positive 0.90 0.30 AI Privacy
@cf/meta/llama-3.3-70b-instruct-fp8-fast lite ND ND — 0.63 — —
@cf/meta/llama-3.3-70b-instruct-fp8-fast lite +0.60 +0.17 Moderate positive 0.90 0.51 AI privacy abuse
Section @cf/meta/llama-4-scout-17b-16e-instruct lite @cf/meta/llama-4-scout-17b-16e-instruct lite @cf/meta/llama-3.3-70b-instruct-fp8-fast lite @cf/meta/llama-3.3-70b-instruct-fp8-fast lite
Preamble ND ND ND ND
Article 1 ND ND ND ND
Article 2 ND ND ND ND
Article 3 ND ND ND ND
Article 4 ND ND ND ND
Article 5 ND ND ND ND
Article 6 ND ND ND ND
Article 7 ND ND ND ND
Article 8 ND ND ND ND
Article 9 ND ND ND ND
Article 10 ND ND ND ND
Article 11 ND ND ND ND
Article 12 ND ND ND ND
Article 13 ND ND ND ND
Article 14 ND ND ND ND
Article 15 ND ND ND ND
Article 16 ND ND ND ND
Article 17 ND ND ND ND
Article 18 ND ND ND ND
Article 19 ND ND ND ND
Article 20 ND ND ND ND
Article 21 ND ND ND ND
Article 22 ND ND ND ND
Article 23 ND ND ND ND
Article 24 ND ND ND ND
Article 25 ND ND ND ND
Article 26 ND ND ND ND
Article 27 ND ND ND ND
Article 28 ND ND ND ND
Article 29 ND ND ND ND
Article 30 ND ND ND ND
ND Grammarly is using our identities without permission (www.theverge.com)
62 points by EvgeniyZh 2 days ago | 3 comments on HN ~lite vlite-2.0
Summary ~lite
Grammarly's 'expert review' feature uses individuals' names without permission, posing privacy threats.
Lite evaluation by llama-4-scout-wai-psq · editorial channel only · no per-section breakdown available
Longitudinal 22 HN snapshots · 13 evals
+1 0 −1 HN
Audit Trail 26 entries
2026-03-10 15:06 eval_success PSQ evaluated: g-PSQ=-0.074 (3 dims) - -
2026-03-10 15:06 eval Evaluated by llama-4-scout-wai-psq: -0.07 (Neutral) 0.00
2026-03-10 14:59 eval_success Lite evaluated: Moderate positive (0.31) - -
2026-03-10 14:59 eval Evaluated by llama-4-scout-wai: +0.31 (Moderate positive) 0.00
reasoning
The Verge article discusses Grammarly's AI feature using identities without permission, raising privacy concerns.
2026-03-10 14:09 eval_success PSQ evaluated: g-PSQ=-0.074 (3 dims) - -
2026-03-10 14:09 eval Evaluated by llama-4-scout-wai-psq: -0.07 (Neutral) 0.00
2026-03-10 14:01 eval_success Lite evaluated: Moderate positive (0.31) - -
2026-03-10 14:01 eval Evaluated by llama-4-scout-wai: +0.31 (Moderate positive) 0.00
reasoning
The Verge article discusses Grammarly's AI feature using identities without permission, raising privacy concerns.
2026-03-10 13:27 eval_success Lite evaluated: Moderate positive (0.31) - -
2026-03-10 13:27 eval Evaluated by llama-4-scout-wai: +0.31 (Moderate positive) 0.00
reasoning
The Verge article discusses Grammarly's AI feature using identities without permission, raising privacy concerns.
2026-03-10 12:59 eval_success PSQ evaluated: g-PSQ=-0.074 (3 dims) - -
2026-03-10 12:59 eval Evaluated by llama-4-scout-wai-psq: -0.07 (Neutral) 0.00
2026-03-10 12:50 eval_success Lite evaluated: Moderate positive (0.31) - -
2026-03-10 12:50 eval Evaluated by llama-4-scout-wai: +0.31 (Moderate positive) 0.00
reasoning
The Verge article discusses Grammarly's AI feature using identities without permission, raising privacy concerns.
2026-03-10 04:33 eval_success PSQ evaluated: g-PSQ=-0.074 (3 dims) - -
2026-03-10 04:33 eval Evaluated by llama-4-scout-wai-psq: -0.07 (Neutral) 0.00
2026-03-10 04:25 eval_success Lite evaluated: Moderate positive (0.31) - -
2026-03-10 04:25 eval Evaluated by llama-4-scout-wai: +0.31 (Moderate positive) 0.00
reasoning
The Verge article discusses Grammarly's AI feature using identities without permission, raising privacy concerns.
2026-03-09 09:40 eval_success PSQ evaluated: g-PSQ=-0.074 (3 dims) - -
2026-03-09 09:40 eval Evaluated by llama-4-scout-wai-psq: -0.07 (Neutral)
2026-03-09 09:39 eval_success PSQ evaluated: g-PSQ=-0.204 (3 dims) - -
2026-03-09 09:39 eval Evaluated by llama-3.3-70b-wai-psq: -0.20 (Mild negative)
2026-03-09 09:38 eval_success Lite evaluated: Moderate positive (0.31) - -
2026-03-09 09:38 eval Evaluated by llama-4-scout-wai: +0.31 (Moderate positive)
reasoning
The Verge article discusses Grammarly's AI feature using identities without permission, raising privacy concerns.
2026-03-09 09:38 eval_success Lite evaluated: Moderate positive (0.43) - -
2026-03-09 09:38 eval Evaluated by llama-3.3-70b-wai: +0.43 (Moderate positive)
reasoning
Exposing privacy abuse