Blog
AI at Your Job

Coding and DevOps with AI

Write, review, test and debug code, ship releases and run cloud systems faster using AI assistants and practical guides.

29 articles · Updated Nov 19, 2026

Most read by people in Engineering, IT and Operations.

An overhead flat-lay photograph of small silicon memory chips knolled with precision electronics tools and computer components in a precise grid.
Local AI ·

Is the 24GB RTX 5080 Cancelled? Best GPUs for Local AI

Reports say Nvidia cancelled a 24GB RTX 5080. Here is why 24GB matters for 30B models and what to buy instead, from a used 3090 to 32GB cards.

RTX 5080 24GB cancelled24GB GPU local AIused RTX 3090 local LLM
Overhead flat-lay photograph of red marker pens, blank paper sheets, and neutral desk supplies laid out at perfect right angles.
AI Agents & Automation ·

What Is a Skill Editor? Keep Your AI Skills Improving

A skill editor reviews weeks of past chats to refine your other AI skills without overfitting to one conversation. Here is how it works, with a template.

skill editorimprove Claude skillsAI skills maintenance
Tiny figurines work together using construction equipment to fit a Raspberry Pi Pico into a 3D-printed enclosure, building a giant hardware desk gadget.
AI Coding Tools ·

How to Design Hardware With Claude Fable 5.2, Step by Step

Use Claude Fable 5.2 to spec parts, write firmware, make STL enclosures and get an assembly guide. A walkthrough of a Raspberry Pi Pico desk gadget.

Fable 5.2 hardware engineeringClaude 3D printed enclosureRaspberry Pi Pico AI project
A primary cursor drops a massive swarm of miniature cursors into an empty folder to assemble the windows and panels of an operating system.
AI Agents & Automation ·

How Did Fable 5.2 Coordinate 1,000 Agents to Build an OS?

Anthropic says Fable 5.2 ran 1,000+ sub-agents for 8 days to build a bootable OS from an empty folder. Here's what that shows and what it means for you.

Fable 5.2 1000 agentsAI built operating systemmulti-agent coding Claude
Tiny figurines pack condensed data blocks into the memory modules of a giant graphics card.
Local AI ·

Can You Run Nvidia Nemotron 3.5 Bolt 74B on 24GB?

Nvidia's Nemotron 3.5 Bolt 74B A9B stores experts at 2 bits to fit in 24GB. See the memory math, speed on RTX Spark, and what you give up.

Nemotron 3.5 BoltNemotron 74B A9B2-bit model 24GB