Resources

Content & Tutorials

Tutorials, market analysis, conference talks, and video content published regularly under the brand The Gateway Guy.

Featured Video

YouTube — The Gateway Guy

View channel →

Latest Videos

Konnect Tutorial: Deploying a self hosted Konnect Kong Gateway Manually
YouTube

Konnect Tutorial: Deploying a self hosted Konnect Kong Gateway Manually

Create, Explore, Manage: Improving Developer Experience with Konnect Developer Portal
YouTube

Create, Explore, Manage: Improving Developer Experience with Konnect Developer Portal

Kong Hackathon 2025 Winner - Kong Auto Rollback AI Agent
YouTube

Kong Hackathon 2025 Winner - Kong Auto Rollback AI Agent

How do you protect your upstream services while limiting your consumers?
YouTube

How do you protect your upstream services while limiting your consumers?

Building Effective API Strategies for Engineers and Architects
YouTube

Building Effective API Strategies for Engineers and Architects

Speaking

Watch Andrew's conference talks →

View All Talks

Market awareness & analysis

dev.to Articles

View all →
OpenAI's first custom chip just benchmarked past NVIDIA. Jalapeño changes the inference equation.
aiopenaiinfrastructure

OpenAI's first custom chip just benchmarked past NVIDIA. Jalapeño changes the inference equation.

OpenAI just published benchmark results for Jalapeño — its first custom AI inference chip — and the...

26 Aug 2026
2 min readArticle
MCP just went stateless. Here's what the new roadmap builds next.
aiapillm

MCP just went stateless. Here's what the new roadmap builds next.

The Model Context Protocol team published an updated roadmap this week, and it's worth reading beyond...

26 Aug 2026
3 min readArticle
Small Models Are Coming for the Cloud — And the Data Is Damning
aillmcloud

Small Models Are Coming for the Cloud — And the Data Is Damning

A Stanford research team just published a paper that should make every hyperscaler investor...

21 Aug 2026
3 min readArticle
The Local LLM Stack in 2026: What Actually Works
aillmprogramming

The Local LLM Stack in 2026: What Actually Works

Running a language model locally used to be a hobbyist experiment. In 2026, it's a viable engineering...

21 Aug 2026
4 min readArticle
Who's really winning open models in 2026? It's not who you think
aimachinelearningllm

Who's really winning open models in 2026? It's not who you think

HuggingFace just published their biannual State of Open Models report covering January to August...

15 Aug 2026
3 min readArticle
The real LLMOps risk isn't the model. It's shadow AI.
kubernetesdevopsai

The real LLMOps risk isn't the model. It's shadow AI.

Large language models broke the clean "train it, test it, ship it" model of production ML. The thing...

14 Aug 2026
2 min readArticle
DeepSeek's Flash outpaced its own flagship. The upgrade was post-training, not parameters.
aillmmachinelearning

DeepSeek's Flash outpaced its own flagship. The upgrade was post-training, not parameters.

DeepSeek shipped V4-Flash-0731 last week — same 284B parameter architecture as the preview, same 13B...

9 Aug 2026
2 min readArticle
Cedar could stop one bad tool call. Dogwood stops bad sequences.
aikubernetesdevops

Cedar could stop one bad tool call. Dogwood stops bad sequences.

AWS launched Dogwood this week — an open-source policy language (Apache 2.0) for AI agent runtime...

9 Aug 2026
3 min readArticle
Andrew Ng at Berkeley: AGI is a contract term, the jobocalypse is a myth, and bubble risk is in the wrong layer
aillmcloudnative

Andrew Ng at Berkeley: AGI is a contract term, the jobocalypse is a myth, and bubble risk is in the wrong layer

At the UC Berkeley Agentic AI Summit last week, Andrew Ng sat down with Sequoia's Alfred Lin for a...

9 Aug 2026
2 min readArticle