Alignment Is an Algorithm Problem: Why RL Can't Optimize "Don't Harm Humans"
MillionInt · x · 2026-09-14
An X post argues alignment is not as hard as claimed but is fundamentally an algorithmic problem the ML community largely abandoned. Pretraining optimizes next-token prediction, not alignment; RL environments for alignment are expensive and rely on hackable proxies; and RL needs failed rollouts, which is unacceptable when failures mean harming real humans. Two paths forward: train in simulations with simulated harm (never perfect), or invent a new algorithm that teaches models not to harm humans without harming anyone in the process.
Related event: Debate Flares Over Whether AI Alignment Is Solvable(3 posts)→
More from AGI Musings
- Walden Robotics CTO: general-purpose robot manipulation is having its 'GPT moment' — adnothing · 2026-10-30
- AI isn't eliminating developers, it's changing their roles, argues analyst — DavidLinthicum · 2026-10-30
- Goldman Sachs says AI will eliminate nearly 15 million jobs — saibharadwaj · 2026-10-30
- Stripe spends 1% of OpEx on tokens — bull case for digital labor — zephyr_z9 · 2026-10-30
- Amazon blocks shopping agents, but these 11 retailers still welcome them — thisiskp_ · 2026-10-30
- Lab insiders know alignment is unsolvable but can't say it until the Overton window shifts — danfaggella · 2026-10-30