Artjoms Stukans

mentions 2 type Person feed RSS

// recent coverage 2 mentions

04:20

2026-08-31

dev.to

ai-safety

The Gate That Stayed Silent — When a Blocker Count That Drops Reads as Improvement

A developer identified a critical failure mode in their deterministic safety gates for AI plan evaluation: when a gate stops firing, blocker counts drop and the improvement masks a regression. The fix…

23:05

2026-08-29

dev.to

artificial-intelligence

Two Projects, One Problem — What PlannerCritic and AdversarialDebate Each Got Wrong

A developer built two LLM-based systems, PlannerCritic and AdversarialDebate, to detect when an LLM's judgment is wrong. Both systems proved reliable but shared a blind spot: their safety metrics impr…

// co-occurs with top 2 entities

PlannerCritic 1 AdversarialDebate 1

// topics top 4 topics

ai safety 2 developer tools 2 artificial intelligence 1 ai agents 1