OpenClaw founder: Don't run high-risk tasks with small models; there's a risk of cue word injection.

This article is machine translated
Show original

According to 1M AI News , the founder of OpenClaw pointed out that small or older models like Claude-Haiku-4.5 lack cue word injection protection, making them vulnerable to leaking confidential information or performing high-risk operations under hacker attacks. He suggested that they should only be used for simple tasks or in environments without permissions.

Source
Disclaimer: The content above is only the author's opinion which does not represent any position of Followin, and is not intended as, and shall not be understood or construed as, investment advice from Followin.
Like
Add to Favorites
Comments