LLMs’ “Bullsh*t” problem, DARPA, and testing for nonsense

Defence research agency looks to challenge the "fundamental gaps between state-of-the-art AI systems and national security applications"

Edward Targett

Jun 18, 2024 - 4 min read

The tendency of large language models (LLMs) to “hallucinate” continues to trouble CIOs eyeing production use-cases – even as efforts around fine-tuning and retrieval augmented generation-based optimisations continue.

Get the full story: Subscribe for free

Join peers managing over $100 billion in annual IT spend and subscribe to unlock full access to The Stack’s analysis and events.

Subscribe now

Already a member? Sign in

Success! You now have access to additional content.