49 articles · page 1 of 3

Prompt engineering, tested: six tricks, 411 answers, scored by code

We ran six popular prompting techniques against developer tasks on three models and scored every answer with code. Three helped everywhere, one did nothing, two depended on the model. Here are the prompts, the numbers, and a script to test your own.

LLM Mart · Nov 6, 2026 4 views

Attention from scratch: a step-by-step tutorial in NumPy

How a transformer works out that 'it' means the cat: dot products, softmax and a weighted sum, built in about a dozen lines of NumPy and worked by hand, number by number.

LLM Mart · Oct 18, 2026 15 views

The AI-in-production safety playbook

Fourteen posts of being wrong in production, compressed to checkboxes

LLM Mart · Sep 30, 2026 11 views

The control plane was flapping because of a spinning disk

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

LLM Mart · Sep 29, 2026 15 views

The overlay that pinged but wouldn't carry TCP

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

LLM Mart · Sep 28, 2026 14 views

Bringing a cluster back after the host rebooted

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

LLM Mart · Sep 27, 2026 8 views

The agent is running in *your* shell

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

LLM Mart · Sep 26, 2026 28 views

How to create and share a Claude Code plugin

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

LLM Mart · Sep 25, 2026 10 views

The scaffolding that made it safe

None of the safety came from the model. It came from six boring habits.

LLM Mart · Sep 25, 2026 9 views

Claude Code skills vs. subagents: when to use each

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

LLM Mart · Sep 24, 2026 12 views

Knowing when to stop

Six hours in, one step left, everything green, and the incident that didn't happen

LLM Mart · Sep 24, 2026 9 views

CLAUDE.md vs. skills: where should Claude Code instructions live?

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

LLM Mart · Sep 23, 2026 24 views

Those are the other app's keys

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

LLM Mart · Sep 23, 2026 8 views

How to use remote MCP servers with the OpenAI Responses API

An API request routing a model's tool call through an approval gate to a remote MCP server

LLM Mart · Sep 22, 2026 11 views

The coverage audit before you delete the safety net

31 config keys, two audits, and why the first one was wrong in both directions

LLM Mart · Sep 22, 2026 13 views

How to publish an MCP server to the official MCP Registry

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

LLM Mart · Sep 21, 2026 17 views

Rotating a leaked credential, in the right order

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

LLM Mart · Sep 21, 2026 9 views

MCP authentication explained: OAuth, scopes, and safe token handling

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

LLM Mart · Sep 20, 2026 14 views

Byte-identical or bust

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

LLM Mart · Sep 20, 2026 12 views

MCP stdio vs. Streamable HTTP: which transport should you use?

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

LLM Mart · Sep 19, 2026 19 views

Never let the AI print a secret

The most important rule wasn't about what I could change. It was about what I was allowed to display.

LLM Mart · Sep 19, 2026 7 views

MCP tools vs. resources vs. prompts: when to use each

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

LLM Mart · Sep 18, 2026 26 views

How to test an MCP server with MCP Inspector

Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.

LLM Mart · Sep 17, 2026 15 views

How to build an MCP server in TypeScript: step-by-step

Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.

LLM Mart · Sep 15, 2026 14 views