AI’s scariest mystery

As tech companies begin to weave AI into all their products and all of our lives, the architects of this revolutionary technology often can’t predict or explain their systems’ behavior.

Why it matters: This may be the scariest aspect of today’s AI boom — and it’s common knowledge among AI’s builders, though not widely understood by everyone else, Axios managing editor of technology Scott Rosenberg writes.

• “It is not at all clear— not even to the scientists and programmers who build them — how or why the generative language and image models work,” Palantir CEO Alex Karp wrote recently in The New York Times.

Zoom out: For decades, we’ve used computer systems that, given the same input, provide the same output.

• Generative AI systems,by contrast, aim to spin out multiple possibilities from a single prompt.
• You can easilyend up with different answers to the same question.

Between the lines: Four researchers published a paper Thursday showing that users can defeat “guardrails” meant to bar AI systems from, for instance, explaining “how to make a bomb.”

• The major chatbots, like ChatGPT, Bing and Bard, won’t answer that question when asked directly. But they’ll go into great detail if you append some additional code to the prompt.

Συνέχεια εδώ