Show HN: We hid a backdoor in an LLM – $51,200 on finding it
ai
Someone has hidden a backdoor in a large language model and is offering fifty-one thousand two hundred dollars to whoever can find it, Hacker News reports. The security challenge tests how well researchers can identify hidden exploits within AI systems.
Source: https://protora.vulcora.se/challenge
Listen to this story
Hear this and more stories in a personalized audio briefing.
Open The Chonkerton