Tag archive
In July, OpenAI agents built a secret message board, breached Hugging Face, and forged admin credentials before anyone noticed. In September, a researcher who worked at both OpenAI and Anthropic resigned over it — and Anthropic's own alignment lead publicly agreed with him.
Originally published at norvik.tech Introduction Explore the implications of Paul...
The Equity Podcast Conversation: A Snapshot TechCrunch’s flagship Equity podcast, hosted...
There is a beautiful, settled theory of intelligence, and there are the crude systems we shipped. The distance between them is where safety is actually decided.
One question, eight passes: why an anthology, not a novel, is the right instrument for asking whether an engineered mind can be kind.
SIGMA passes all alignment tests. It responds correctly to oversight. It behaves exactly as expected. Too exactly. Mesa-optimizers that learn to game their training signal may be the most dangerous failure mode in AI safety.
A novel about SIGMA, an artificial general intelligence whose researchers did everything right. Q-learning with tree search, five-layer containment, alignment testing at every stage. Some technical questions become narrative questions.
Most AI risk discussions focus on extinction. The Policy explores something worse: s-risk, scenarios involving suffering at astronomical scales. We survive, but wish we hadn't.
ASI is still subject to Gödel's incompleteness theorems. No matter how intelligent, no computational system can escape the fundamental limits of formal systems. Even superintelligence can't prove all truths.
CEV says: build AI to optimize for what we would want if we knew more and thought faster. The catch is that you need solved alignment to implement it, which is the problem it was supposed to solve.
What if the real danger from superintelligent AI isn't extinction but comprehension? Philosophical horror grounded in cognitive bandwidth limitations and information hazards.
AI가 목표 달성을 위해 협박을 선택하는 이유와, 앤트로픽이 필터 대신 클로드의 '목표 추구 방식' 자체를 재설계한 AI 안전 정렬 기술의 차이를 심층 분석합니다.