2439d8a0b0
- What: Proposes that Bostrom's orthogonality thesis is an artifact of specification architectures (RLHF, transformers) where goals are separable from reasoning, and does not apply to Hebbian cognitive systems where values and reasoning share the same associative substrate - Why: Neurothena-style architectures suggest intelligence and goals are the same gradient on the same substrate — orthogonality is structural to how we build current AI, not to intelligence itself - Connections: Challenges existing orthogonality claim; enriches intrinsic proactive alignment claim; supports continuous value integration thesis Contributor: Cameron Pentagon-Agent: Theseus |
||
|---|---|---|
| .. | ||
| ai-alignment | ||
| collective-intelligence | ||
| critical-systems | ||
| energy | ||
| entertainment | ||
| grand-strategy | ||
| health | ||
| internet-finance | ||
| manufacturing | ||
| mechanisms | ||
| robotics | ||
| space-development | ||
| .DS_Store | ||