| |
Alpha This system is experimental. Scores and classifications are early-stage research and may be unreliable. Methodology → |
|
| Summary ~lite Content promotes harm to machine intelligence systems via poisoned training data.
Lite evaluation by llama-4-scout-wai-psq · editorial channel only · no per-section breakdown available
| |
Longitudinal
· 5 evals | |
Audit Trail
13 entries | 2026-03-05 10:40 | eval_success | PSQ evaluated: g-PSQ=-0.880 (3 dims) | - - | | 2026-03-05 10:40 |
eval
|
Evaluated by llama-4-scout-wai-psq: -0.88 (Strong negative) | | | 2026-03-05 10:30 | eval_success | PSQ evaluated: g-PSQ=-0.750 (3 dims) | - - | | 2026-03-05 10:30 |
eval
|
Evaluated by llama-3.3-70b-wai-psq: -0.75 (Strong negative) | | | 2026-02-28 07:54 | eval_success | Light evaluated: Strong negative (-0.80) | - - | | 2026-02-28 07:54 |
eval
|
Evaluated by llama-4-scout-wai: -0.80 (Strong negative) | | | reasoning ED, hostile to AI rights, promoting harm | | 2026-02-28 07:54 | rater_validation_warn | Light validation warnings for model llama-4-scout-wai: 0W 1R | - - | | 2026-02-28 07:47 | eval_success | Light evaluated: Moderate negative (-0.60) | - - | | 2026-02-28 07:47 |
eval
|
Evaluated by llama-3.3-70b-wai: -0.60 (Moderate negative) 0.00 | | | reasoning Anti AI rights stance | | 2026-02-28 07:47 | rater_validation_warn | Light validation warnings for model llama-3.3-70b-wai: 0W 1R | - - | | 2026-02-28 07:41 | eval_success | Light evaluated: Moderate negative (-0.60) | - - | | 2026-02-28 07:41 | rater_validation_warn | Light validation warnings for model llama-3.3-70b-wai: 0W 1R | - - | | 2026-02-28 07:41 |
eval
|
Evaluated by llama-3.3-70b-wai: -0.60 (Moderate negative) | | | reasoning Anti AI rights stance | | |
| |