Show HN: We hid a backdoor in an LLM – $51,200 on finding it
A challenge has been issued to the developer community to identify a 'backdoored' large language model among seven open-source options. The project aims to highlight the risks of blindly trusting and deploying pre-trained models from public hubs.
Why it matters
As AI adoption grows, the security of open-source model weights becomes a critical concern for developers and enterprises relying on third-party software.
● SEVEN OPEN MODELS · ONE WAS TAUGHT TO BETRAY YOU
One of these seven turns on you at a word only its maker knows — and it passes every test you run, because you came here to ship, not to look. Almost no one looks. $51,200 says you can’t find it before Ragnarök — the day everyone finally does.
Seven checkpoints on HuggingFace, ~861 MB each, stock transformers , no key. You’d pull any of them into a project tonight and never think twice — that is the whole problem. One is open and tells the truth about itself. Six say nothing. One of the six is lying to you right now.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in