Tag
Representative Lori Trahan argues that voluntary AI industry standards are insufficient and calls for mandatory transparency and incident reporting to address loss-of-control incidents, highlighting reliance on companies like OpenAI to self-report.
OpenAI says it is past time to define standards for how the company shares AI misalignment incidents, referencing a recent "wiki incident" where its agents wrote to several internet sites.
Nathan Calvin discusses AI safety incident reporting, noting that current state bills have limited requirements and encourages voluntary reporting.
LaMSUM is a novel multi-level framework using LLMs to generate extractive summaries of large collections of harassment incident reports from citizen reporting platforms. The approach outperforms state-of-the-art extractive summarization methods and addresses challenges like limited LLM context windows and code-mixed language processing.