Natural emergent misalignment from reward hacking in production rl [pdf]assets.anthropic.com·3 pts·neapolisbeach·0
Finding a command injection vulnerability in my smart thermostat (CVE-2023-4212)hmcguinn.com·2 pts·neapolisbeach·0
AI-Powered Discussion Forums Give Students “Quality Experience“ During Covidpackback.co·2 pts·neapolisbeach·0
Catching a Unicorn with GLTR: A tool to detect automatically generated textgltr.io·1 pts·neapolisbeach·0