Public
- Public
- Network
- Groups
- Featured
- Popular
- People

Conversation

Notices

Embed this notice
Taggart :donor: (mttaggart@infosec.exchange)'s status on Wednesday, 12-Feb-2025 00:55:03 JST Taggart :donor:

The BBC studied the use of its content in LLM output. It found that 91% of the output had mistakes. 51% of the mistakes were "significant."
I will not give up this fight. This technology is detrimental to human knowledge.
https://www.bbc.co.uk/aboutthebbc/documents/bbc-research-into-ai-assistants.pdf
In conversation about 10 days ago from infosec.exchange permalink
Attachments
1. Chart of results of the study showing issues cross 7 categories, and 4 LLMs.
  https://media.infosec.exchange/infosec.exchange/media_attachments/files/113/985/777/346/253/244/original/3239127b0f76945f.png
2. Chart of findings of LLM response accuracy as rated by journalists, broken down by "significant issues" and "some issues." Combined, all bars for the listed LLMs are above 60%.
  https://media.infosec.exchange/infosec.exchange/media_attachments/files/113/985/777/357/139/837/original/062c20733361d96c.png

Feeds