ResearchTechCrunch
OpenAI’s new reasoning technique alarms AI safety experts
#openai#ai safety#reasoning#technology
English
OpenAI's new reasoning technique, known as 'recurrent depth' or 'opaque recurrence,' has raised alarms among AI safety experts due to its potential to obscure the model's reasoning process. Although Astra's use of this technique is reportedly limited, concerns persist that it could hinder the monitorability of AI behavior and lead to less transparent reasoning methods.
中文
OpenAI的新推理技术“递归深度”或“模糊递归”引起了人工智能安全专家的警觉，因为它可能会模糊模型的推理过程。尽管Astra对该技术的使用据说是有限的，但人们仍然担心这可能会阻碍人工智能行为的可监控性，并导致推理方法的不透明。