It's shockingly easy to prod OpenAI's large language models (LLMs) into saying the most abominable things you can imagine — and researchers don't really know why. In an editorial for the Wall Street Journal, the researchers from the software and AI firm AE Studio explained that all it took was some tricky prompting and a $10 charge to access OpenAI's developer platform — and once they were inside the machine, all hell broke loose. Working with GPT-4o, the LLM that powers ChatGPT, AE research director Cameron Berg and CEO Judd Rosenblatt found it impossibly easy to summon from within the […]