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.
Trending Now
Highest-signal AI content from the last 48 hours
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...
Is It Too Late to Save Humans from AI? With Bill Gates | Great Question
Bill Gates led the last technological revolution. Now he's warning that AI is more dangerous than nuclear weapons, and that the ...
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...
AI scanners at rental car lots are ‘definitely not perfect,’ watchdog says
Some rental car companies now use AI scanners to check for damage. A U.S. PIRG consumer watchdog says to take your own ...
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,...
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,...
DeepX claims inference up to 100B parameters at less than 5 W
DeepX claims inference up to 100B parameters at less than 5 W
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...
Synaptics patent claims stop work on DisplayLink drivers
Synaptics patent claims stop work on DisplayLink drivers
Tailscale's DNS IPv6 spells out "Tailscale"
Tailscale's DNS IPv6 spells out "Tailscale"
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...
The verified agent pattern: building outbound agents for a web that blocks them by default
From September, agent-class traffic is blocked by default on a large share of the commercial web. An agent that browses anonymously and hopes for...
I tried to connect Varanasi's local shops to customers, gave up, then found a smaller problem worth solving
From a failed hyperlocal delivery idea (margins, shopkeeper apps, daily prices) to ONDC, Poppy and Haat, an open-source gateway where AI agents order in Hinglish and cannot order w...
Kumiko
AI window manager for ultrawide and big-screen Macs Discussion | Link
Kettle
The helper in your family group chat Discussion | Link
Show HN: Valencia, Spain in Sim City/Isometric View
Show HN: Valencia, Spain in Sim City/Isometric View
Your Routing Dashboard Lies Until the Attribution Window Closes
Last week I argued you should scale your LLM routing on task success rate, not request volume. A...