James Read

@jamesread
46 Followers
40 Following
263 Posts

A "full stack" Open Source enthusiast, creating http://olivetin.app, and other no-nonsense open source software.

Dad, hobbyist developer, open-source enthusiast and Red Hatter. Find my Blog, GitHub and contact details at http://jread.com

Code, Containers & Cloud bloghttps://blog.jread.com
GitHubhttps://github.com/jamesread
Homepage, and more of mehttps://jread.com
I have to say I'm really enjoying #cursor 3; being able to switch between multiple projects in the agents view at once, without having multiple instances open is a real game changer.
Dune: Part Three | Official Teaser Trailer

Experience the epic conclusion. Dune: Part Three only in theaters December 18 #DuneMovie #FilmedforIMAXDirected by Denis Villeneuve and written by Villeneuve...

YouTube
"Half-width numbers" - oops, that literal translation didn't work so well :-)
Japella now supports image posting to Mastodon, X and Twitter. :-) https://github.com/jamesread/japella
"Hey AI, how are my #Kubernetes deployments?" - using MCP servers on your LAN is with LLMs in the Cloud;
#n8n #automation #ai #mcp https://blog.jread.com/posts/local-mcp-access-via-n8n/
Local MCP Access via n8n: Let Cloud LLMs Use Your Local Tools

Use n8n as a bridge so that LLMs running in the cloud can discover and call tools on your local MCP servers—without moving your data or your MCP stack to the cloud.

James Read's Code, Containers & Cloud blog
Just because you can, doesn't mean you should.
Testing image posting.
OliveTin is getting more security scrutiny; and it's a good thing

OliveTin has been getting a lot of security scrutiny this week - as there’s been a relatively huge surge of security advisories come for the first time. I imagine that the project has been listed in a security forum or similar, and AI tools (and human eyeballs) are being used to looking for security vulnerabilities. This is a good thing, and I welcome more security reports, that will be patched, and will make OliveTin better.

James Read's Code, Containers & Cloud blog

AI tools are moving fast—from fancy autocomplete to fully autonomous development teams.

The real question isn’t whether to use AI, but how much autonomy to give it.

I put together a simple 0–5 model to describe these levels of autonomy in practice:

https://blog.jread.com/posts/ai-levels-of-autonomy-in-software-engineering/

AI Levels of Autonomy in Software Engineering

AI tooling for software engineering has moved quickly from fancy autocomplete to the verge of fully autonomous engineering. Most people can see that AI adds value. The real question is no longer whether to use AI, but how much autonomy to give it. Capability alone doesn’t justify maximising autonomy everywhere. You have to match autonomy to risk. This post defines a simple scale of autonomy levels and where I draw my own lines.

James Read's Code, Containers & Cloud blog
My purchasing power for gadgets exceeds my free time to actually play with them. ;-)