Current AI “alignment” is just a mask Our findings in @WSJ explore the limitations of today’s alignment techniques and what’s needed to get AI right 🧵 https://t.co/2GEsQvl2kV

Can large language models take the place of traditional search engines? For us to have confidence in them, we would need to know that they haven’t been fed propaganda and conspiracy theories—we’d need to know that the jpeg is capturing the right sections of the Web. But, even if a large language model includes only the information we want, there’s

... See more

The illusion itself is not the core concern. Those discussing ChatGPT often invoke its distant ancestor, the Eliza “psychotherapist” chatbot developed in 1967 that produced a similar illusion. By modern standards Eliza was primitive: it generated responses via simple heuristics, often rephrasing input as a question or making generic comments.... See more