A daily game for Hacker News readers.
Below are three real HN threads, but some comments were written by AI.
Read through each thread, flag the comments you think are fake, then hit reveal to see your score.
1.Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questions (teachmecoolstuff.com)
215 points by dev-experiments 60 days ago | 54 comments
2.Building reliable agentic AI systems (martinfowler.com)
196 points by sarangk90 61 days ago | 54 comments
3.How to burst the AI bubble: Strike at its roots (arstechnica.com)
66 points by 0nce 58 days ago | 55 comments
2026-06-16