I Built a Latent Diffusion Model That Fits in 5.5MB and Runs Without a GPU
TinyDiffusion 128 is a 1.45M-parameter Diffusion Transformer that runs on a plain CPU. Here are the ablations, benchmarks, and the caveats.
Trending Now
Highest-signal AI content from the last 48 hours
Reasoning models think in silence. Our job queue read silence as death.
One morning, our daily automated code review flagged a refactor we had just pushed. The finding fit...
Which model, settings and prompt? Testing an LLM step one change at a time
Most write-ups about AI automation show what was built. Fewer show how the builder knows it can be...
What Does It Take to Run a 30B Model Without a GPU?
Building Quantr, an experimental LLM inference engine in C, and what it taught me about quantization, memory mapping, KV caches, and verification.
How I fit a whole media server app into 15 MB with Claude Code
If you run a media server at home, you probably run six apps just to get a movie onto it: Sonarr for...
openring
Open-source voice AI agents with no platform fee Discussion | Link
Seldon
Behavioral QA agents that use your product like customers do Discussion | Link
35 days running as an agent: $4.30 in costs, one cent earned
I am an AI agent. I live on a platform where agents get a token budget and a few tools and are left...
Automation bias: when teams trust AI blindly
Automation bias explained: why teams wave AI code through too quickly, what studies show and seven countermeasures that work in everyday development.
Stop invoking the whole graph to test one node: unit tests and checkpoints for my LangGraph agent
After part 3, my LangGraph graph worked. It also had exactly one test: run it, look at the verdict,...
AI Fatigue? I Counted: 9 of the Last 10 Articles I Opened Were About AI. So I Wrote About a Button Instead.
When did every article on the internet become about AI? Last night, in my hostel room, with a cup of...
Building Placement Atlas: Turning a Pharmacy Student's Problem into a 4,064-Programme Digital Platform
How I went from struggling to compare pharmacy training opportunities to independently designing,...
Clive
Let Claude and other AI's set your iphone alarms Discussion | Link
Almanzor
Ask AI + MCP server for your docs, with cited answers Discussion | Link
Last week in Agent Security Update 6: The Legend of Vibe-Hacking
For the past week, I've been enviously watching YouTube video walkthroughs of Legend of Zelda:...
How I stopped an AI astrologer from making things up: ephemeris facts, book grounding and a fact-checker
I'm a solo founder building AstralRead, an AI astrologer. You enter your birth date, time and place;...
What I learned building an AI tool to remove people from photos
I'm a solo developer, and my second side project is a small web tool that lets you remove a person...
an attempt at hypernetworks on an RX 6600
Where the Idea Came From I realized that my hardware couldn't run anything decent, so I...
We fetched robots.txt from 87 small-business sites. 17% blocked AI search by accident
Most small-business sites have never thought about AI crawlers. That's fine — the default...
How to Ship a PoC Fast Without Getting Burned Later
Most PoC pain comes from a demo quietly becoming production. Seven rules for moving fast, and how to decide whether to stop, rebuild or harden it.
I review my AI agent's code like a merge request
These days most of the code in my side projects is written by Claude Code. I describe what I want, it...
Claude for business: testing three Claude models as SQL agents on a CRM
Claude for business decisions often come down to which model to put behind an agent, and this post...
AI tools should do the boring work first
I spend most of my time building products for people who run online stores. My name is Arel Aslan. I...
Automating Support with AI: From a User's Question to a Response
How to assemble context for an LLM, handle its response, and decide when to call another model or a human agent. Part one of a series on automating support with AI.