Posts tagged “AI”

Compression and LLMs are trying to solve the exact same problem: predicting what comes next. Learn the fundamentals of compression and how better prediction leads to better shrinkage.

Annie Sexton

•

~3.7K words

•Topics:

• AI

What is an AI gateway, and do you need one in 2026? How AI gateways route, secure, and observe LLM and agent traffic — and when one is essential.

Sam Richard

•

~1.2K words

•Topics:

• AI
• Agents

A complete guide to what quantization is, how it works, and how it's used to compress large language models

Sam Rose

•

~6.9K words

•Topics:

• AI

Two weeks with a self-improving coding agent taught me more about LLMs than a year of prompting ever did.

Joel Hans

•

~4.1K words

•Topics:

• AI

The AI Gateway now supports Anthropic's SDK natively so you build with Claude-only features like prompt caching, extended thinking, and more.

Nijiko Yonskai

•

~300 words

•Topics:

• AI
• Product updates

An explanation of 14 benchmarks you're likely to see when new models are released.

Sam Rose

•

~8.8K words

•Topics:

• AI

A far more detailed explanation of prompt caching than anyone asked for: how tokens, embeddings, and attention make cached LLM tokens 10x cheaper and faster.

Sam Rose

•

~6.1K words

•Topics:

• AI

Route AI requests to OpenAI, Anthropic, Google, and self-hosted models through one endpoint, with automatic failover, key rotation, and CEL-based selection.

Nijiko Yonskai

•

~700 words

•Topics:

• AI
• Product updates

Our original 2025 take: the AI gold rush created a modern problem — too many shovels (models), too little gold (control). Are AI gateways the fix?

Aaishika S Bhattacharya

•

~1.1K words

•Topics:

• AI

Vijil’s platform tests your in-development agents against failure modes like prompt injection, PII leaks, and hallucinations—with a bit of help from ngrok.

Joel Hans

•

~1.8K words

•Topics:

• AI
• Customers

The shortest path to the best of all worlds: AI-driven automation, simple deployments with containers and a GUI, and a gateway to knit it all together securely.

Joel Hans

•

~1.8K words

•Topics:

• Traffic Policy
• AI

Smithery is building tools to help you build, test, and distribute your MCPs on one side, and a "Google for MCPs" on the other—here's how they do it with ngrok.

Joel Hans

•

~800 words

•Topics:

• SDKs
• AI
• Customers

Are search and AI bots invading your ngrok endpoints? Fight back with three developer-friendly traffic policies you can deploy in minutes.

Joel Hans

•

~1.5K words

•Topics:

• Traffic Policy
• AI
• Security

Building LLM-fueled apps? See how one AI startup uses ngrok to develop locally against remote services and safely test LLM prompt changes without breaking prod.

Team ngrok

•

~600 words

•Topics:

• AI
• Customers

Your simplest path to AI collaboration or development using ngrok and Deepseek with an assist from Ollama and a GPU-accelerated virtual machine.

Joel Hans

•

~2.3K words

•Topics:

• AI

Explore how ngrok enhances AI development by enabling secure, direct access to customer data, ensuring data integrity and privacy.

Joel Hans

•

~2.4K words

•Topics:

• AI
• Security

Explore how ngrok empowers AI companies with connectivity solutions, aiding rapid development and innovation in AI technology.

Sam Richard

•

~600 words

•Topics:

• AI
• Customers

Learn how to build a ChatGPT-like SMS chatbot using the OpenAI API and Twilio Programmable Messaging with Python.

Lizzie Siegle

•

~1.2K words

•Topics:

• AI
• SDKs