Building a WhatsApp AI Chatbot That Hands Off to a Human: Architecture and Pitfalls
Getting a language model to answer WhatsApp messages takes an afternoon. Getting it to stop answering...
Tutorials
AI/ML Research Digest — Oct 31, 2026
Accelerated inference & algorithmic efficiency Gradient‑recovery speculative decoding...
The code in AI programming hints that wasn't the student's: half of it ended up in their final submission
Made with AI agents working in my name. Code Apache-2.0, text CC BY 4.0. Only counts are published:...
AI Can Write Code. Engineers Still Have to Make It Work.
Marc Benioff and Mark Zuckerberg have made bold predictions about AI and software engineering. But...
Day 13/90: Define What Your AI Tools Can Accept—and What They Must Return
Day 13/90: Define What Your AI Tools Can Accept—and What They Must Return An LLM chooses a...
Your AI Agent Remembers Things. Who Audits What It Remembers?
The problem nobody talks about AI agents are getting persistent memory. mem0, Zep, Letta,...
How a Trusted Extension Name Delivered an SSH Backdoor Through Cursor's Store
A tampered Claude Code extension sat in Cursor's marketplace for about 11 hours. Here is the delivery chain that made it look like a normal update.
Ollama in Houdini: 60 VEX Tests on a 16GB RTX 5070 Ti
Originally published by Alicia on 2 November 2026 at Digital Garden. Original measurements and...
FDE, Part 2: Discover AI Requirements and Define Pilot Acceptance
Observe real tasks, review data and compare against a baseline to turn business goals into testable acceptance criteria.
With DeepSeek's update, I want to know whether there will be less rework
DeepSeek Search and Fetch fit into a writing workflow. What matters to me is reading the sources, checking the facts and saving time all the way through revision.
A 200K-Token Claude Session Left Idle Re-Buys Its Cache: $0.04 Becomes $1.00
On Opus 5.5 a warm 200K-token Claude session reads its history for $0.04. Let the cache expire and the next line pays $1.00 to write it back. Do the math.
How to Sell Usage Credits in Your AI App (Pay-as-You-Go Without Surprises)
Selling credits in your AI-built app? Packs vs monthly allowance, what happens at zero, refunds of unused credits, and what to test on Polar or Stripe.
TanStack AI vs Vercel AI SDK: The One I Would Ship
I installed both SDKs and read their type surfaces. TanStack AI 1.0 vs Vercel AI SDK 7 on protocol, typing, agent loops, durability, and lock-in.
I built for a keyword Google Trends says doesn't exist
Disclosure: I work on FORMAT, a tool that turns interior renders into short videos. The keyword data...
4,300 tests, written by an AI: how they were planned, run and enforced
If an AI writes your code, your tests are the only thing standing between "it compiles" and "it's...
Once the token limit was raised, AI feedback changed English learners' words more often
Made with AI agents working in my name. Code Apache-2.0, text CC BY 4.0. Only counts are published:...
Few-shot examples teach format, not facts: how to pick, balance and order them
Monday AI Insight. Most of us add few-shot examples to a prompt the same way: grab three or four that...
EU AI Act in Force: What Developers Must Do Now
The EU AI Act is now fully enforceable. A practical developer checklist for Article 50 disclosure, AI content marking, GPAI duties and fines.
Build a BPE Tokenizer in 80 Lines of TypeScript and Watch JSON Eat Your Tokens
Train a toy byte-pair encoder in TypeScript and print every merge. Then ask o200k_base why pretty JSON and long keys cost you more tokens.
How much VRAM do popular LLMs really need at 4-bit and 8K context? Data from 26 models
"Will it fit on my card?" comes up constantly in local-LLM threads, and the usual answer is a rule of...
FoodBridge: From “Where Can I Find Food?” to First Place at Hack for Humanity 🏆
This is a submission for the MLH x DEV Writing Challenge Finding a food pantry is one step. Knowing...
I shipped my biggest project ever and felt… nothing
Last month I finished one of the largest side project of my career — an open-source framework, docs,...
Part 12: What carried over from series 1 (and what did not)
Part 12 · One Agent, Five Platforms Series 1 designed one agent on one platform: a change-approval...
The AI Architecture Decision You Need to Make Before It's Too Late
An honest take on where AI agents, LLMs, and production systems actually are right now -- from someone deep in the space.