| |
Alpha This system is experimental. Scores and classifications are early-stage research and may be unreliable. Methodology → |
|
| Summary ~lite T-Mobile's password management criticized for storing passwords in clear text.
Lite evaluation by llama-4-scout-wai-psq · editorial channel only · no per-section breakdown available
| |
Longitudinal
· 6 evals | |
Audit Trail
12 entries | 2026-03-05 22:37 | eval_success | PSQ evaluated: g-PSQ=-0.234 (3 dims) | - - | | 2026-03-05 22:37 |
eval
|
Evaluated by llama-4-scout-wai-psq: -0.23 (Mild negative) | | | 2026-03-05 22:26 | eval_success | PSQ evaluated: g-PSQ=-0.170 (3 dims) | - - | | 2026-03-05 22:26 |
eval
|
Evaluated by llama-3.3-70b-wai-psq: -0.17 (Mild negative) | | | 2026-02-28 16:03 | eval_success | Lite evaluated: Mild positive (0.10) | - - | | 2026-02-28 16:03 |
eval
|
Evaluated by llama-4-scout-wai: +0.10 (Mild positive) 0.00 | | | reasoning ED, criticizing T-Mobile's password storage and customer service | | 2026-02-28 16:01 | eval_success | Lite evaluated: Mild positive (0.20) | - - | | 2026-02-28 16:01 |
eval
|
Evaluated by llama-3.3-70b-wai: +0.20 (Mild positive) 0.00 | | | reasoning Exposing security abuse | | 2026-02-28 15:58 | eval_success | Lite evaluated: Mild positive (0.10) | - - | | 2026-02-28 15:58 |
eval
|
Evaluated by llama-4-scout-wai: +0.10 (Mild positive) | | | reasoning ED, criticizing T-Mobile's password storage and customer service | | 2026-02-28 15:57 | eval_success | Lite evaluated: Mild positive (0.20) | - - | | 2026-02-28 15:57 |
eval
|
Evaluated by llama-3.3-70b-wai: +0.20 (Mild positive) | | | reasoning Exposing security abuse | | |
| |