friendly reminder: #halucinations are no temporary bug soon being solved

https://www.computerworld.com/article/4059383/openai-admits-ai-hallucinations-are-mathematically-inevitable-not-just-engineering-flaws.html

Tried asking a Large Lying Model (LLM) something about firewall configuration on Ubiquity network devices in combination with WireGuard VPN.

I was very specific about which device it was, which software version it was running and what I wanted to achieve. The models answered confidently, but the answers were all complete garbage and simply wrong.

#ai #llm #nerworking #halucinations #it