Don’t Expect Quick Fixes in ‘Red-Teaming’ of AI Models. Security Was an Afterthought
White House officials concerned by AI chatbots’ potential for societal harm and the Silicon Valley powerhouses rushing them to market are heavily invested in a three-day competition ending Sunday at the DefCon hacker convention in Las Vegas. Some 2,200 competitors tapped on laptops seeking to expose flaws in eight leading large-language models representative of technology’s next big thing. But don’t expect quick results from this first-ever independent “red-teaming” of multiple models. Findings won’t be made…
Read More
