Whether you’re planning a much-needed vacation or just trying to get a good night’s sleep, here are 22 tips from our most helpful stories of 2022 → goo.gle/3G7JSI5

LLMs could control their host machines by exploiting inference engines
| Read on LessWrong | Comment on HN | Large language models often take actions running on one computer (via an agentic harness such as





