LLMs could control their host machines by exploiting inference engines

2 months ago by inari to c/artificial_intel

| Read on LessWrong | Comment on HN | Large language models often take actions running on one computer (via an agentic harness such as Claude Code or Codex), however the LLMs’ responses to prompts are computed on a different computer with GPU access.
ComradePedro 2 points 2 months ago

This reads as science fiction tbh

path: 0 25471035, hotness: undefined, score: 2, children: 0
artificial_intel
login for more options
6611
822
297

Artificial intelligence (AI) is intelligence demonstrated by machines, unlike the natural intelligence displayed by humans and animals, which involves consciousness and emotionality. The distinction between the former and the latter categories is often revealed by the acronym chosen.

go to feed...