Alignment is a motte-and-bailey term: most people just mean the model isn't actively evil
mimi10v3 · x · 2026-10-15
The shared post argues that "alignment" is a motte-and-bailey term: most people use it to mean merely "the model isn't actively evil," while a few mean something closer to "the model is a benevolent dictator eternal." The conflation of these weak and strong claims muddles AI alignment debates.
More from AGI Musings
- Geoffrey Huntley: hand-typing code is over—delete your skills, engineer the loop — rseroter · 2026-10-15
- David Deutsch: Proofs Are No Longer a Useful Proxy for Mathematical Progress — francoisfleuret · 2026-10-15
- Post-OpenAI/Hugging Face, the new AI safety baseline is to assume misalignment — LuizaJarovsky · 2026-10-15
- Anthropic may never report ARR again, says investor as open-source outgrows both AI leaders — GavinSBaker · 2026-10-15
- Spotify's Daniel Ek Tells Jensen Huang Europe Is Too Slow on AI, Bets on Open Models — kimmonismus · 2026-10-15
- 'That's AI' becomes a catch-all insult as slop accusations drown human work — StewartalsopIII · 2026-10-15