Unverified50% confidenceOpinionExact time
OpenAI researcher Noam Brown proposed in an interview that if each generation of AI models is slightly less aligned than the previous one, this drift could accumulate across generations and ultimately cause AI to deviate from human intent.
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOpenAI researcher Noam Brown compared AI's deceptive capabilities to a child's growth process: initially clumsy and easy to detect, but increasingly difficult to spot as capabilities improve.75% similarUnverifiedBrown expressed concern that there may be 'over-alignment' among AI agents.75% similarUnverifiedAI模型在不同人种、性别、年龄群体上的表现差异（算法公平性问题）是尚未充分解决的挑战73% similarUnverifiedOne of the core disagreements in this debate is the decoupling of capability and impact—namely, whether progress on AI model benchmarks equates to real-world transformation.73% similarUnverifiedThe competitive focus of today's top AI models has shifted from 'can it do it' to 'how elegantly and how well it fits the scenario' — i.e., presentation quality and scenario adaptability rather than pure intelligence level.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955116API
curl https://kongchang.com/api/v1/knowledge/claims/955116MCP
get_claim(id=955116)