Oliver Prompts(@oliviscusAI):nvidia's moat just got a citation problem exposed. researchers built a way to trace a bad citation in a deep research report back to the exact agent that broke it, not just flag that something's wrong. applied to nvidia's #1-ranked open source system, 84.7% of the final report's errors trace back to the orchestrator, even though it's nowhere near the worst individual agent on its own. worth noting: two one-line prompt fixes raised citation recall by 5 points, but recall still sits around 64-70% after that, so this isn't solved.

Oliver Prompts

@oliviscusAI

Helping you understand AI. Software Engineer. Opinions are personal. DM for collabs.

加入 May 2022

11 正在关注 20.9K 粉丝

Oliver Prompts@oliviscusAI

2026.08.26 03:05

nvidia's moat just got a citation problem exposed. researchers built a way to trace a bad citation in a deep research report back to the exact agent that broke it, not just flag that something's wrong. applied to nvidia's #1-ranked# open source system, 84.7% of the final report's errors trace back to the orchestrator, even though it's nowhere near the worst individual agent on its own. worth noting: two one-line prompt fixes raised citation recall by 5 points, but recall still sits around 64-70% after that, so this isn't solved.

显示更多