Have LLMs Finally Mastered Geolocation? - bellingcat (www.bellingcat.com)
from gedaliyah@lemmy.world to technology@lemmy.world on 06 Jun 15:12
https://lemmy.world/post/30921391

Back in July 2023, Bellingcat analysed the geolocation performance of OpenAI and Google’s models. Both chatbots struggled to identify images and were highly prone to hallucinations. However, since then, such models have rapidly evolved.

#technology

threaded - newest

underline960@sh.itjust.works on 06 Jun 22:11 next collapse

All the models, at some point, returned answers that were entirely wrong. ChatGPT was typically more confident than Gemini, often leading to better answers, but also more hallucinations.

No.

!savedyouaclick@lemmy.world