Day 15/90: Deterministic Intent Routing — Does Your Request Reach the Right Workflow?
An AI application can produce a clear, confident response after sending a request to the wrong...
Tutorials
Which day should we drive? Watching border queues with Home Assistant and a vision model
Every holiday season we sit in the same queue and wonder if we picked the wrong day. So I made Home Assistant watch public traffic cams and let an LLM score what it sees.
Logging a Change Is Not the Same as Being Able to Undo It
There's a draft spec going around for giving AI agents real undo — not a confirmation dialog before...
I Built a Daily Sports Card Game in a Month With AI Agents. Here's Everything It Broke.
I'm not an engineer. I come from the sales world. But between June 18 and July 16, I pushed 172...
A retention policy nobody chose
When our tests finished, the computer deleted the folders that held each run's evidence. Nobody told...
Where Claude's usage limits went: from SSE to protobuf frames
I maintain Claude Monitor, an open-source browser extension that shows claude.ai's usage limits: the...
I scored 12 AI models on whether they admit they don't know. My own token limit nearly broke the test.
Most AI leaderboards ask whether the model got it right. I wanted to know something else: when it's...
What You See Is What You Sign: the consent record agents are missing
There's a good argument going around right now that an agent's log tells you what it did but keeps no...
Can an agent buy from you? A one-cent till, six refusals, and twelve cold agents
Most agent-payment demos stop at the happy path: an agent hits an endpoint, gets a 402, signs a...
Comparing Batch and Real-Time LLM Inference Economics
Batch inference costs 50% less than real-time inference at Anthropic, OpenAI and Google, in exchange...
I built a malware-triage AI skill — then realized malware could talk it into lying
I'm a cybersecurity student, and I wanted to see how well an AI agent could help with the first,...
Why KV-Cache Memory Tricks — Not New Math — Drove This Week's Biggest Inference Wins
LLM inference digest (Oct 28–Nov 4, 2026): elastic KV-cache offloading, MoE-tuned speculative decoding, and day-0 serving for Mistral Large 4.
AI-Assisted Data Entry in Laravel: Treat LLM Output Like Untrusted User Input
The demo went great. We dropped a supplier quote PDF into the app, the model read it, and three...
Mitigating WebSocket Retry Storms: Preventing Server-Side Thread and Event-Loop Starvation
Mitigating WebSocket Retry Storms: Preventing Server-Side Thread and Event-Loop...
Smoke-test agent UI with keyboard-only before you merge
I used to treat “tab through the page” as an a11y nicety — something for the checklist after visual...
StateRoot: shared intelligence and versioned work across AI agents
Hi DEV, I use several AI agents on cheaper subscriptions, switching to conserve usage limits and...
Your LiveKit agent works great on WebRTC. The phone network will humble it
A voice agent that works perfectly in your browser can fall apart the moment someone calls it from a...
I migrated off my no-code stack and regretted it. For nine days.
I migrated our whole setup off a pile of tools onto one app a couple of months ago. For the first...
An Open Letter to Anthropic Founders: The Training Data Paradox and AI’s Arbitrary Borders
I rely on Claude Pro daily for professional engineering and backend development. On October 20,...
Two Months, Five People: Building the Backend Behind Foodmartex’s Next Chapter
Over the past two months, our five-person team at Foodmartex has built catalogue-grounded AI...
The KV Cache From Scratch
In every part of this series, one thing kept showing up: the notebook. In Part 1 it grew by 72 KB...
WebMCP vs MCP vs browser-use: which agents should call (2026)
WebMCP vs MCP vs browser-use in 2026: Chrome's page tools, durable MCP servers, and DOM actuation. When to use each layer, with primary sources checked 4 November.
Weight-Space Programming: how GPT-6 Astra edited Qwen's weights and took MATH-500 from 7.9% to 48.1%
MIT CSAIL's weight-space programming: GPT-6 Astra edited 0.016% of Qwen3.5-0.8B's weights with no gradients and lifted MATH-500 from 7.9% to 48.1%. How it works.
Did Someone Repost My Malfoid AI Portrait? Finding Crops, Flips and Screenshots With Perceptual Hashes (Python, Tested)
You made a Malfoid (Female Malfoy / Fem Draco) portrait, posted it, and a week later a picture that...