Researchers based in Washington and Chicago have developed ArtPrompt, a new way to circumvent the safety measures built into large language models (LLMs). According to the research paper ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs, 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 ArtPrompt tool. It is a simple and effective attack, and the paper provides examples of the ArtPrompt-induced chatbots advising on how to build bombs and make counterfeit money. — Read More
Daily Archives: March 13, 2024
Nearly a third of consumers think AI has improved workplace productivity
Artificial Intelligence (AI) is a tricky subject! Some feel it’s making their life much easier, while others feel it will impact society positively. Some feel it needs to be regulated and some feel brands need to be transparent about how they use it. Love it or hate it, you just cannot ignore it. In this piece, we’re asking consumers how they feel the technology has impacted productivity in their workplace.
A recent YouGov survey asked consumers across 17 international markets to what extent they feel AI systems like ChatGPT and Bard have improved or hindered overall productivity in their workplace over the last year. — Read More
Rick's Cafe AI 