When 2+2=5

·Hacker News··

Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions.

Read full article →

Related Articles

Road to Elm 1.0
wolfadex · Hacker News · 3h ago
Nintendo announces new product revisions in Europe with replaceable batteries
akyuu · Hacker News · 2h ago
New AI tutor achieves 0.71-1.30 SD effect size in Dartmouth course [pdf]
jonahbard · Hacker News · 20h ago
“Beyond the limit”: Satellites and mirrors in space pose threat to the night sky
Breadmaker · Hacker News · 1d ago
A sociotechnical threat model for AI-driven smart home devices
dijksterhuis · Hacker News · 22h ago