Topic
20 articles found
Originally published on hexisteme notes, part of a series on building and running an AI agent fleet. To stop an AI research or RAG agent from presenting its own inferences as retrieved facts, split the work so the LLM never decides what is a fact: let the LLM only extract and summarize, and let a de
The idea Prop firm traders (people who trade with other people's money) need specific calculators that account for strict drawdown rules. Every existing calculator is either ugly, full of ads, or doesn't know that FTMO has a 5% daily drawdown limit. So I built PropWise — 10 interactive tools across
We've all done it: pasted an API key into a file "just to test," then a week later after the secret is already committed. So I built Secret Guardian, a VS Code extension that catches secrets live, in , the moment they appear — and visually masks them so they never show 👉 Secret Guardian on the VS C
The agent we built in Part 6 is sharp — it plans, chains tools, and answers genuinely hard questions. It also has the memory of a goldfish. Ask it "when does the AI Club meet?", get a good answer, then ask "how many days until that?" — and it has no idea what "that" is. Every question starts from a
Stop Shipping Broken Env Config: Comparing 4 TypeScript Validators Odejobi Abiola Samuel Jun 22 #typescript #node #javascript #webdev 1 reaction Add Comment 4 min read
ForgeIL Has Been Self-Hosting Since May. Nobody Found It Yet. It got quiet here for a month. Not because the project stalled, but because life moved. I moved aboard my ketch, Deep Blue, now anchored in Rostock. A new band started rehearsing at a spot near the Admiralbrücke in Kreuzberg, we even foun
Hi, I'm Ryan, CTO at airCloset. This post is about unifying a production codebase spanning 46 repositories across multiple services into one knowledge graph, using static analysis. Internally we call it code-graph, and I built it between January and March of this year. Three things I want to write d
GitHub put a normal-sounding feature into public preview this month: cloud and local sandboxes for Copilot. Normal is doing a lot of work there. The release says Copilot can now run inside secure, isolated sandboxes, either locally on the developer machine or in a GitHub-hosted cloud environment. Lo
Public pushback against data centers has emphasized their water and energy consumption, and now Nvidia is highlighting its claim that the Rubin generation reference design for a fully liquid-cooled data center has "eliminated massive amounts of power usage and pretty much all water usage." Still, it
All the ways to watch Norway vs Senegal live streams for free, as Erling Haaland & Co. aim to build on their impressive opening victory at the World Cup 2026.
Walmart goes head to head with Amazon Prime Day — and the deals are seriously good! Here's everything worth shopping this week.
More software solutions to the hardware crisis are on their way
According to one of the most prolific and well-known tipsters on Weibo, the upcoming iPhone 18 Pro will get the much-rumored main camera upgrade. Actually, he says it's "confirmed". This upgrade basically means the main camera module will be physically larger on the iPhone 18 Pro than it was on its
Before I released my own AI chatbot plugin, I ran it through a security review. It came back with 35 bugs, three of them critical, and the one that made my stomach drop was an HTML injection coming straight out of unsanitized model output. At the time, that felt like my low point as a developer. The
When a Constructor Became a Security Boundary I was auditing the initialization layer of one of my Rust systems when I noticed something that looked completely harmless. A constructor accepted an object that wasn't fully valid yet and relied on a later validation step to reject it if something was w
Originally published on the Invoance blog. Most teams treat AI outputs like ephemeral function returns. The model responds, the response goes to the user, maybe a row gets written to a database, and that is the entire trail. When a customer disputes an answer six months later, when a regulator asks
My first meeting at Converse was a 50-person standup. The scrum lead had every engineer type their status into an application. She would present it. Then they would read it off the screen, one by one, as the rest of us watched. Twenty software engineers. Six QA. Status after status after status, rea
This is a topic many beginners overlook until they encounter performance issues in production. One of the biggest surprises for developers is discovering that an application that worked perfectly during development suddenly becomes slow when real users start using it. A Django application serving te
To run a task every 5 minutes in Python you need Celery + Redis + Celery Beat + a worker process + a dedicated Dockerfile. In Fitz it's a decorator. With retry, timezone, persistence, and catch-up inside the language. Your client is happy with the API. It's running. Then they ask for three things: "
Para correr una task cada 5 minutos en Python necesitás Celery + Redis + Celery Beat + worker process + Dockerfile dedicado. En Fitz es un decorador. Con retry, timezone, persistencia y catch-up adentro del lenguaje. Tu cliente está contento con la API. Está corriendo. Entonces te pide tres cosas: "
