Bellingcat Tests LLM Geolocation: Big Gains, Humans Still Essential

Bellingcat evaluated Anthropic's claim of 'superhuman' LLM geolocation capabilities, finding significant improvements over prior models but concluding that human analysts remain indispensable for verification and context. The assessment highlights both the potential of AI in open-source intelligence and its current limitations, underscoring the need for human oversight in high-stakes geolocation tasks.

AI disclosure: Model-written summary of the source, not a verified fact. Check the sources. How Mosaic works