llm-behaviour
Found 5 posts tagged with "llm-behaviour".
Benchmark Gaming: Why Leaderboard Scores Mislead
2026-03-033 min
That impressive benchmark score? It might reflect test leakage, judge bias, or selective disclosure. Why LLM leaderboards are less reliable than they look.
Over-Refusal: When Safety Training Goes Too Far
2026-02-134 min
Safety alignment backfires when models refuse benign requests. Why 'How do I kill a Python process?' gets flagged, and what this means for usability.
AI Hallucinations: Why Models Confabulate
2026-01-233 min
LLMs don't have intent - but they can confabulate. Why next-token prediction leads to confident nonsense, and how to spot it.
AI Slop: Recognizing Low-Quality AI Content
2026-01-094 min
Merriam-Webster's 2025 Word of the Year is 'slop' - AI-generated content with no real value. How to recognize it and avoid producing it.
AI Sycophancy: When Your AI Agrees Too Much
2026-01-024 min
Your AI might tell you what you want to hear. What sycophancy is, why it happens, and how to prompt around it.