home / www.washingtonpost.com / item 45278740
Summary ~lite AI security rights Advocates
Exposes DeepSeek AI security issues
Lite evaluation by llama-3.3-70b-wai · editorial channel only · no per-section breakdown available
Audit Trail
17 entries
2026-02-28 08:30 eval_success Light evaluated: Mild positive (0.28) - - 2026-02-28 08:30
eval
Evaluated by llama-4-scout-wai : +0.28 (Mild positive) 0.00 2026-02-28 08:30 rater_validation_warn Light validation warnings for model llama-4-scout-wai: 0W 1R - - 2026-02-28 08:24 eval_success Light evaluated: Mild positive (0.28) - - 2026-02-28 08:24
eval
Evaluated by llama-4-scout-wai : +0.28 (Mild positive) 2026-02-28 08:24 rater_validation_warn Light validation warnings for model llama-4-scout-wai: 0W 1R - - 2026-02-28 08:14 eval_success Light evaluated: Moderate positive (0.50) - - 2026-02-28 08:14
eval
Evaluated by llama-3.3-70b-wai : +0.50 (Moderate positive) 2026-02-28 08:14 rater_validation_warn Light validation warnings for model llama-3.3-70b-wai: 0W 1R - - 2026-02-26 06:06 dlq Dead-lettered after 1 attempts: DeepSeek writes less secure code for groups China disfavors? - - 2026-02-26 06:06 dlq Dead-lettered after 1 attempts: DeepSeek writes less secure code for groups China disfavors? - - 2026-02-26 05:51 credit_exhausted Credit balance too low, retrying in 242s - - 2026-02-26 05:48 credit_exhausted Credit balance too low, retrying in 251s - - 2026-02-26 05:35 dlq Dead-lettered after 1 attempts: DeepSeek writes less secure code for groups China disfavors? - - 2026-02-26 05:23 credit_exhausted Credit balance too low, retrying in 320s - - 2026-02-26 05:06 dlq Dead-lettered after 1 attempts: DeepSeek writes less secure code for groups China disfavors? - - 2026-02-26 04:56 credit_exhausted Credit balance too low, retrying in 244s - -