TomsHardware Posted March 7 Share Posted March 7 Researchers have developed ArtPrompt, a new way to circumvent the safety measures built into large language models (LLMs). According to their research paper, chatbots such as GPT-3.5, GPT-4, Gemini, Claude, and Llama2 can be induced to respond to queries they are designed to reject using ASCII art prompts generated by their tool. View the full article Quote Link to comment Share on other sites More sharing options...
.png.6dd3056f38e93712a18d153891e8e0fc.png.1dbd1e5f05de09e66333e631e3342b83.png.933f4dc78ef5a5d2971934bd41ead8a1.png)
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.