-
Apr 3, 2024, 4:41 pm143 pts
Slashdot
How do you get an AI to answer a question it's not supposed to? There are many such "jailbreak" techniques, and Anthropic researchers just found a new one, in which a large language model (LLM) can be convinced to tell you how to build a bomb if you prime it with a few dozen less-harmful questions first. From a…
Trending Today on Tech News Tube
Tech News Tube is a real time news feed of the latest technology news headlines.
Follow all of the top tech sites in one place, on the web or your mobile device.
Follow all of the top tech sites in one place, on the web or your mobile device.
