From Cloud Dependency to Local Intelligence: The Future of Accessible AI
Intel on AI29 Okt 2025

From Cloud Dependency to Local Intelligence: The Future of Accessible AI

As AI models grow more powerful, the question of where they run is becoming just as important as what they do. In this episode, Brandon Weng, Co-Founder and CEO of Fluid Inference, unpacks what it takes to move AI from massive data centers to everyday devices—and why that shift matters.

Brandon shares the story behind Fluid Inference, a company focused on making it easier for developers to deploy large AI models like transformers on consumer hardware. From pivoting away from his previous project, Slipbox, to the technical and philosophical choices that shaped Fluid's direction, he walks us through the thinking behind local-first AI. We explore the tradeoffs between cloud-based and on-device inference—touching on privacy, cost, control, and performance—and the hardware breakthroughs that are making edge AI more viable, including integrated NPUs in devices like Intel's AI PCs.

#EdgeAI #OnDeviceInference #AIOptimization #PrivacyFirst #OpenSourceAI #LocalAI

Episoder(137)

Making Machine Learning Application Development Easy with Ray and Anyscale – Intel on AI – Episode 50

Making Machine Learning Application Development Easy with Ray and Anyscale – Intel on AI – Episode 50

In this Intel on AI podcast episode: Today, the deluge of data has made demand for machine learning engineers explode. Also because distributed computing is a challenging and elite subfield of compute...

9 Apr 202010min

Teaching Machines to Recognize Human Emotions with Entropik Tech and Intel – Intel on AI – Episode 49

Teaching Machines to Recognize Human Emotions with Entropik Tech and Intel – Intel on AI – Episode 49

In this Intel on AI podcast episode: Knowing how a product or service makes a customer feel enables companies to make successful products that their customers enjoy. Yet measuring this traditionally t...

8 Apr 202012min

Unlocking the Potential of Your Data with Nuveo OCR and Xeon Scalable – Intel on AI – Episode 48

Unlocking the Potential of Your Data with Nuveo OCR and Xeon Scalable – Intel on AI – Episode 48

In this Intel on AI podcast episode: Manually gathering, processing, and analyzing unstructured data is extremely effort and time intensive. For industries such as insurance or finance this is a big i...

7 Apr 202011min

Predicting the Future of Fashion with IFDAQ and Intel – Intel on AI – Episode 47

Predicting the Future of Fashion with IFDAQ and Intel – Intel on AI – Episode 47

In this Intel on AI podcast episode: Gauging prospects and predicting the direction of the fashion industry is incredibly difficult. Businesses and investors hypothesizing the success of rising stars ...

26 Feb 202010min

AI and Sound Analytics Driving Value in Manufacturing Operations – Intel on AI – Episode 46

AI and Sound Analytics Driving Value in Manufacturing Operations – Intel on AI – Episode 46

In this Intel on AI podcast episode: One of the biggest challenges manufacturing operations face when adopting digitalization and intelligence is the cost and complexity to instrument existing machine...

13 Feb 202012min

Altoros PDF Mining and Car Damage Assessment Optimized for Xeon Processors – Intel on AI – Episode 45

Altoros PDF Mining and Car Damage Assessment Optimized for Xeon Processors – Intel on AI – Episode 45

In this Intel on AI podcast episode: When making car insurance claims it can take a lot of time to have a claims adjuster inspect the damage to your car and then get the estimate from a body shop revi...

6 Feb 202010min

AI Powered Digital Risk Protection with ZeroFOX – Intel on AI – Episode 44

AI Powered Digital Risk Protection with ZeroFOX – Intel on AI – Episode 44

In this Intel on AI podcast episode: Today, social media is among the primary business and communication platforms for modern organizations, yet, social media networks are incredibly large platforms w...

6 Feb 202010min

HCL Optimized Edge Analytics using Intel Distribution of OpenVINO toolkit – Intel on AI – Episode 43

HCL Optimized Edge Analytics using Intel Distribution of OpenVINO toolkit – Intel on AI – Episode 43

In this Intel on AI podcast episode: The process of diagnosing a patient with chest abnormality is done by radiologists and doctors with a lot of experience and expertise. This involves looking for th...

10 Jan 202010min

Populært innen Politikk og nyheter

giver-og-gjengen-vg
aftenpodden
aftenpodden-usa
popradet
forklart
lydartikler-fra-aftenposten
stopp-verden
dine-penger-pengeradet
rss-gukild-johaug
det-store-bildet
rss-ness
nokon-ma-ga
hanna-de-heldige
fotballpodden-2
aftenbla-bla
rss-penger-polser-og-politikk
rss-dannet-uten-piano
rss-utenrikskomiteen-med-bogen-og-grasvik
e24-podden
bt-dokumentar-2