Artwork
iconShare
 
Manage episode 393408824 series 3350329
Content provided by Tarek Madany Mamlouk. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Tarek Madany Mamlouk or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://staging.podcastplayer.com/legal.

Apple secretly released Ferret, an open-source large language model integrating language understanding with image analysis.

In a surprising move, Apple has quietly launched Ferret, an open-source large language model developed in collaboration with Cornell University, as reported by Dataconomy. Unlike traditional language models, Ferret combines language understanding with image analysis, allowing it to analyze specific regions of images and respond to prompts involving both text and visuals. The release signifies Apple's move towards openness, presenting challenges in scaling against larger models like GPT-4 due to infrastructure limitations. However, the potential impact on Apple devices is immense, promising improved image-based interactions, augmented user assistance, enriched media understanding, and a platform for developer innovation.


Sources:

https://dataconomy.com/2023/12/26/apple-ferret-llm-ai/

https://twitter.com/OpenMedFuture/status/1738540634745536597

https://arxiv.org/pdf/2312.11514.pdf

https://www.techradar.com/computing/artificial-intelligence/apple-may-be-working-on-a-way-to-let-llms-run-on-device-and-change-your-iphones-forever


Hosted on Acast. See acast.com/privacy for more information.

  continue reading

84 episodes