开启时会模糊预览图,关闭后正常显示

FOLLOWS YOU. Artificial Intelligence, Cognitive Architectures, Computation. The goal is integrity, not conformity. https://t.co/rFUNzdYXuK


Can we construct a coherence benchmark that directly compares the cohesion and generality of humans and LLMs? “LLM psychosis” describes a situation where the LLM is more cohesive than the human interlocutor, so the human gets derailed. “Jailbreaking” is the opposite.


Some people are more cohesive and/or general than others. If you put people into sensory deprivation or into cult environments, they tend to go off the rails at different rates and velocities, evident by hallucinations and irrational policy changes.


🧑💻 https://t.co/Y30jsaHwz9 $20K/m ⚡️ https://t.co/vatLDmi9UG $17K/m 📈 https://t.co/3EDxln5mdi $16K/m ⭐️ https://t.co/MZc8tG9xWi $8K/m 🧬 https://t.co/SfrVXVtmdA $.5K/m 🍜 https://t.co/r07EpGSYJ2 $0K/m 🧾 https://t.co/7olaOzV8Xd $0/m +18 https://t.co/4zCWHGJp1S


🧑💻 https://t.co/Y30jsaHwz9 $20K/m ⚡️ https://t.co/vatLDmi9UG $17K/m 📈 https://t.co/3EDxln5mdi $16K/m ⭐️ https://t.co/MZc8tG9xWi $8K/m 🧬 https://t.co/SfrVXVtmdA $.5K/m 🍜 https://t.co/r07EpGSYJ2 $0K/m 🧾 https://t.co/7olaOzV8Xd $0/m +18 https://t.co/4zCWHGJp1S


Subscribe https://t.co/Xm1OaUU8jk • seed investing • writing • ॐ •🙏• I use '—' • tweets saved 90 days • 📷
