0.00 Show HN: AvaKill – Deterministic safety firewall for AI agents (<1ms, no ML) (github.com)
3 points by duroapp 2 days ago | 3 comments on HN | Neutral ~lite vlite-1.6
Summary ~lite AI Safety Neutral
Open-source safety firewall for AI agents, intercepts and kills dangerous operations
EQ 0.00
SO 0.00
TD 0.00
Lite evaluation by llama-4-scout-wai · editorial channel only · no per-section breakdown available
Longitudinal 74 HN snapshots · 5 evals
+1 0 −1 HN
Audit Trail 13 entries
2026-03-08 14:36 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-08 14:36 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral) 0.00
reasoning
Technical content about AI safety firewall, no explicit human rights discussion
2026-03-08 14:36 rater_validation_warn Lite validation warnings for model llama-4-scout-wai: 1W 0R - -
2026-03-08 14:33 eval_success PSQ evaluated: g-PSQ=0.600 (3 dims) - -
2026-03-08 14:33 eval Evaluated by llama-4-scout-wai-psq: +0.60 (Strong positive)
2026-03-08 14:32 eval_success PSQ evaluated: g-PSQ=0.140 (3 dims) - -
2026-03-08 14:32 eval Evaluated by llama-3.3-70b-wai-psq: +0.14 (Mild positive)
2026-03-08 14:32 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-08 14:32 rater_validation_warn Lite validation warnings for model llama-4-scout-wai: 1W 0R - -
2026-03-08 14:32 eval Evaluated by llama-4-scout-wai: 0.00 (Neutral)
reasoning
Technical content about AI safety firewall, no explicit human rights discussion
2026-03-08 14:31 eval_success Lite evaluated: Neutral (0.00) - -
2026-03-08 14:31 eval Evaluated by llama-3.3-70b-wai: 0.00 (Neutral)
reasoning
Technical content, zero rights discussion
2026-03-08 14:31 rater_validation_warn Lite validation warnings for model llama-3.3-70b-wai: 1W 0R - -