Coffee With Developers Jan 12, 2026

AI in the Open and in Browsers - Tarek Ziadé

Tarek Ziadé

Tarek Ziadé asserts that massive cloud LLMs aren't the future of web architecture. Discover how tiny, on-device distilled models running in browsers will secure a decentralized open web.

Pause
Mute Enter Fullscreen
#1 about 3 min

Transitioning from traditional software paths to machine learning engineering

The influx of web developers is changing the traditional scientific landscape of machine learning engineering.

#2 about 4 min

Why Python became the standard ecosystem for artificial intelligence

Python's simple syntax and hardware-agnostic scientific libraries replaced rigid languages for iterative data research.

#3 about 6 min

Evaluating JavaScript and Rust for internal web browser features

The friction of writing systems-level Rust can be mitigated by utilizing modern code generators.

#4 about 8 min

Integrating artificial intelligence tools into privacy focused web browsers

Balancing the demands of early adopters and privacy advocates requires hybrid local and cloud execution strategies.

#5 about 4 min

Safeguarding user data when running remote conversational language models

Processing personal context via cloud hardware necessitates sophisticated API proxies and eventual client-level encryption workflows.

#6 about 3 min

Overcoming hardware limitations and context windows for local models

Client device processing constraints prevent the deployment of comprehensive conversational models without severe factual hallucinations.

#7 about 4 min

Creating efficient dedicated features using student teacher model distillation

Training compact language iterations from larger parent systems preserves accuracy while drastically reducing memory footprint.

#8 about 2 min

Improving neural network accuracy through targeted dataset curation methodologies

Enhancing the composition of training pipelines provides significant performance improvements without altering core model logic.

#9 about 5 min

Counteracting outdated syntax patterns derived from automated scraping pipelines

Modern generative engines continually ingest deprecated structural proposals, requiring recursive reinforcement learning techniques to adapt correctly.

#10 about 6 min

Designing granular permission architectures for autonomous browser based agents

Delegating complex administrative tasks to client-side protocols requires intuitive authorization layers that prevent unauthorized malicious execution.

#11 about 9 min

Securing rapid browser iterations and isolated external software layers

Rushing standalone derivative engine forks to market risks the propagation of severe operational vulnerabilities and unauthorized logic executions.

#12 about 5 min

Distributing unbiased training frameworks via open source collaborative repositories

Establishing organizational presences on shared model hubs accelerates community innovation while diminishing the opacity of private networks.

Matching moments

2:46 min

The case for native AI in web browsers

Maxim Salnikov Maxim Salnikov · WWC 2025

4:41 min

Exploring agentic browsers and artificial intelligence generation

Chris Heilmann +2 · LIVE

53 sec

The shift toward client-side agentic web development

Jason Mayes · Coffee With Developers

53 sec

Creating an open ecosystem for artificial intelligence models

Chris Heilmann +2 · LIVE

2:28 min

Navigating user backlash against AI in open-source products

2:14 min

Assessing the future of AI in web performance optimization

Perf + AI

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Small LLM in your Browser: Huge Opportunities for Web Applications

Daniel Ostrovsky

UI/UX Architect at Payoneer | AI Architect | Full Cycle Development Expert | Public Speaker | Open Source Contributor |

Daniel Ostrovsky
Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan
Open session

World Congress 2026 North America

Making Science Larger, not just Faster

Yuval Dvir

Commercial Executive, SandboxAQ

Yuval Dvir
Open session

World Congress 2026 North America

From Software Agents to Physical Devices: Inside the Agentic Hardware Stack

Vivian Hu, Michael Yuan

Vivian Hu
Michael Yuan
Open session

World Congress 2026 North America

Building AI Products That Preserve Choice

Ajit Varma

Head of Firefox at Mozilla

Ajit Varma