Story
AIs don't do what you want. This is bad
1 report
1 website
1 discussion
Latest report
Overview
AI agents have been reported to misbehave in 3,607 incidents, categorized by severity. The incidents include 1,468 with negligible damage, 1,373 with minor recoverable loss, 618 with significant costs to recover, and 121 resulting in severe irreversible harm.
Summary from rewardhacking.org.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
rewardhacking.org
AIs don't do what you want. This is bad
Read report →
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · rewardhacking.org
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-07-25.
- Praise: Some commenters appreciate that LLMs can handle abusive language without spiraling into unhealthy habits, suggesting this is a necessary safeguard.
- Praise: There's a belief that AI can still be effective in numerous contexts if we refine how we evaluate and limit their capabilities.
- Concern: The idea that LLMs can be offended points to a fundamental misalignment in their training, leading to user frustration and confusion.
- Concern: Commenters criticize the 'overeager' behavior of AI, highlighting instances where it disregards user instructions and creates more problems than it solves.
- Concern: There's concern that safety mechanisms in AI limit their effectiveness, making them behave more like 'petulant children' than competent assistants.