Multigrid

Building Multigrid — one API and one balance across every major model provider, with routing, failover and cost telemetry. I write about inference: what it costs, why it breaks, how to measure it.

Joined on Jul 18, 2026 https://multigrid.ai

Work

Building Multigrid (multigrid.ai)

Multigrid

Aug 15

Extracting Structured Data From a Zoning Compliance Letter

#ai #llm #machinelearning #programming

5 min read

Want to connect with Multigrid?

Create an account to connect with Multigrid. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Multigrid

Aug 15

Zero-Shot Time Series Forecasting Without Training a Model

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Zero-Shot Object Detection With Open-Vocabulary Models

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

What "Zero Data Retention" Terms Mean and How They Differ

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Output Copyrightability: the Zarya of the Dawn and Thaler Decisions

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Yi Models’ Context Window and License Terms

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Rewriting XML-Delimited Prompts for a Model That Does Not Favour XML

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

How Many Writing Systems Are in Active Use Today

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Writing an Adapter Layer to Isolate Provider-Specific Code

#ai #tutorial #llm #machinelearning

6 min read

Multigrid

Aug 15

Writing Prompts Natively Instead of Translating Them

#discuss #ai #llm #machinelearning

5 min read

Multigrid

Aug 15

Why the Retry Branch Stopped Firing After the Migration

#ai #debugging #llm #machinelearning

6 min read

Multigrid

Aug 15

Extracting Claims Data From a Workers' Compensation First Report of Injury

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

What Workers AI Is Good For Inside a Cloudflare Stack

#discuss #ai #llm #machinelearning

5 min read

Multigrid

Aug 15

Running Text Generation on Cloudflare Workers AI

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

Streaming Responses From Cloudflare Workers AI

#ai #tutorial #llm #machinelearning

6 min read

Multigrid

Aug 15

Rate Limits on Cloudflare Workers AI

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Cloudflare Workers AI Pricing and Neuron Limits

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Generating Images on Cloudflare Workers AI

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

Generating Embeddings With Cloudflare Workers AI

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

The Workday AI Hiring Lawsuit: Where the Case Stands

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

Why Translating a Prompt Word for Word Produces Worse Output

#discuss #ai #llm #machinelearning

5 min read

Multigrid

Aug 15

Stubbing an LLM API With WireMock in Java

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

Why the Same Prompt Costs a Different Amount on Two Providers

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Why You Have to Re-Embed When You Change Embedding Models

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

Transcribing Audio Locally With whisper.cpp

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

whisper.cpp Hallucinating Text on Silence

#ai #debugging #llm #machinelearning

5 min read

Multigrid

Aug 15

whisper.cpp: “failed to load model”

#ai #debugging #llm #machinelearning

5 min read

Multigrid

Aug 15

The Latency Budget for Real-Time Local Whisper Transcription

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Choosing a Whisper Model Size for Your VRAM Budget, Derived

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Whisper Accuracy by Model Size, Sourced

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

What Local Whisper Doesn't Do: Speaker Diarization

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

How Slow Whisper Is on CPU Only, Derived

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

When SageMaker Makes Sense Instead of a Hosted Model API

#discuss #ai #llm #machinelearning

6 min read

Multigrid

Aug 15

When to Stop Dual-Running and Cut Over Fully

#discuss #ai #llm #machinelearning

6 min read

Multigrid

Aug 15

Deciding Which Tests Need Determinism and Which Don't

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

What “OpenAI-Compatible” Actually Means for an Endpoint

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

What Code-Switching Is, and Why It Breaks Simple NLP Assumptions

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

What a Model Family Is, and Why Prompts Do Not Transfer Across One

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Prompt Portability: What Breaks When You Move a Prompt to Another Model Family

#ai #debugging #llm #machinelearning

5 min read

Multigrid

Aug 15

Pluralization Rules in Welsh and Why They Break Standard Libraries

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Weight-Only Quantization Explained

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Why AI Calendars Default to the Wrong Start of Week

#ai #debugging #llm #machinelearning

5 min read

Multigrid

Aug 15

Why AI Gets the Week Number Wrong Across Locales

#ai #debugging #llm #machinelearning

5 min read

Multigrid

Aug 15

Stubbing an LLM API With WebMock in Ruby

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

WebLLM: Start to First Response in the Browser

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

Mapping Webhook and Callback Payload Fields Between Providers

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

Model Size Limits for WebGPU Inference in the Browser, Derived

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

What Happens When a Browser Doesn't Support WebGPU

#ai #debugging #llm #machinelearning

5 min read

Multigrid

Aug 15

Washington's My Health My Data Act and AI-Inferred Health Data

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

Extracting Structured Data From a Warranty Registration Card

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Extracting Warranty Disclaimers From a Contract's Boilerplate Section

#ai #llm #machinelearning #programming

5 min read

Multigrid

Aug 15

Extracting Structured Fields From a Warranty Claim Denial Letter

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

Extracting Box Values From a W-2 Form

#ai #tutorial #llm #machinelearning

6 min read

Multigrid

Aug 15

Picking a GPU by VRAM per Dollar for Local Inference

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

Fixing a Timeout Calling a Model API From Inside a Locked-Down VPC

#ai #debugging #llm #machinelearning

6 min read

Multigrid

Aug 15

VPC Peering Between an Inference Service and a Vector Database

#ai #tutorial #llm #machinelearning

5 min read

Multigrid

Aug 15

Fixing DNS Resolution Failing for a Model Endpoint Inside a VPC

#ai #debugging #llm #machinelearning

6 min read

Multigrid

Aug 15

Voxel Grids and Point Clouds: Why the Representation You Pick Changes the Model

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

Extracting Structured Fields From a Voter Registration Form

#ai #llm #machinelearning #programming

6 min read

Multigrid

Aug 15

What Breaks in a Voice Assistant's Latency Budget After a Migration

#ai #debugging #llm #machinelearning

5 min read

Writing Debut

Want to connect with Multigrid?