Why OpenAI’s Astra Could Make AI Doom Harder to Prevent

·LessWrong··

TLDRProvide a non-technical introduction to opaque reasoning.Present evidence for why opaque reasoning is bad.Discuss the major pitfalls of this approach.Gleaming hope amongst the chaos. Excerpt from AI 2027The City That Slowly Lost the Ability to See the Council's DecisionsFor centuries, a city made every important decision in a public hall via a council.Whenever the council chose to build a bridge, go to war, raise taxes, or imprison someone, the members of the council were to debate aloud. Th...

Read full article →

Related Articles

Three sites made 215,128 “best software” pages for AI. Perplexity cites them
jakobgreenfeld · Hacker News · 4h ago
GrapheneOS says Pixel 11 has MTE support after all
user_7832 · Hacker News · 4h ago
The ChatGPT/Codex app bundles a full copy of LibreOffice
timpera · Hacker News · 22h ago
Aging Brains Blend Memories Together Instead of Just Forgetting Them
mdp2021 · Hacker News · 5h ago
The Emergent Symbolic Structure of Artificial Neural Networks
schmuhblaster · Hacker News · 14h ago