Weight-Space Programming: The Third Lever for LLMs
Gradient descent was never sacred. It was scaffolding — the only general-purpose tool we had for shaping billions of numbers no human could read, so we built...
AI & Machine Learning
Explore the latest in artificial intelligence, deep learning, LLMs, and machine learning engineering.
26 articles
The Hidden AI Cost of JavaScript Frameworks
The agent spent eleven minutes reading a migration guide before it wrote a single line of code. Not your agent — the one a colleague pointed at a SvelteKit...
Recommendation-Free Feeds: Curation Over Algorithms
It's 11pm on a Friday. You're tired, you open YouTube, and the homepage greets you with a wall of screaming thumbnails, shocked faces, and the same three...
Why LLM Voice Is Instantly Recognizable — and How to Fix It
Spend ten minutes reading blog posts written since late 2023 and you'll feel it: a creeping sense that everything was written by the same slightly overeager...
Self-Hosting Mistral Large 4: Lessons Learned the Hard Way
When Mistral released the weights for Mistral Large 4 — a roughly 1-trillion-parameter model with about 52 billion active parameters — my inbox filled up with...
Stack Overflow Is Dying: 5 Myths About What Replaces It
Stack Overflow now gets fewer than 1,000 new questions a month — a lower volume than its second month of existence, back in 2008. If you learned to program any...
Offline-First AI: Building an LLM That Works Offline
The power's been out for nine hours, the cell network is overloaded, and the freezer in your garage is full of meat you bought on Saturday. Is it still safe to...
World Models vs Video Prediction: What I Got Wrong
When Genie 4's demos landed, my first reaction was the same one I've had since Sora: this is a very good video generator, why are we calling it a world model?...
LLM Conjecture Generation vs Proof-Checking: Who Wins
Somewhere between the second and third coffee, a lot of complexity theorists recently read a sentence they never expected to read: a deterministic algorithm...
Reasoning Models Are Trained, Not Prompted
Here's an opinion I defended badly at a team lunch last year and have since come to believe even more strongly: if your mental model of a reasoning model is "a...
Specialist CNNs vs Frontier LLMs for Image Classification
A dermatologist recently put 200 biopsy-proven skin lesions in front of two frontier LLMs and a fine-tuned copy of Inception v3, a convolutional network Google...
Full-Duplex Speech Models: 5 Voice AI Myths, Tested
I spent two years building voice assistants on the classic stack: speech-to-text in, language model in the middle, text-to-speech out. Every latency...
DeepSeek's Inference Engine: 5 Myths, Tested
When DeepSeek pushed its production LLM inference engine to GitHub under an Apache 2.0 license, the repo hit thousands of stars in hours. That's not surprising...
Time-Series Foundation Models Make Custom Training Obsolete
Here's a claim that would have gotten me laughed out of any forecasting team five years ago: for most time-series problems, training a model on your own data...
Hybrid Reasoning Agents: Latent Thinking, Text Acting
Here's an uncomfortable truth about LLM agents: most of the tokens they produce are expensive filler. A reasoning agent solving a math problem will happily...
AI Code Comprehension Checks vs Tests: When Each Wins
Here's a scenario that's becoming common: your coding agent writes 600 lines across four files, the tests pass, the linter is happy, and you merge it. Two...
Flash-Tier LLMs Are the Real Inference Efficiency Story
Here's a claim that will annoy a lot of people who spend their days arguing about model leaderboards: for most production LLM workloads, the "smartest" model...
Why AI Benchmarks Miss 90% of Real Work
A friend of mine runs operations at a mid-sized logistics company, and last spring her team spent three weeks evaluating whether an LLM could take over their...
Mechanistic Interpretability Myths Put to the Test
For years, the conventional wisdom in mechanistic interpretability was grim: neural networks are tangled knots, and before you can understand one you first...
Inside an Agentic Coding CLI: Loops, Context, Permissions
The model is the easy part. That's the claim, anyway — and after watching a dozen agentic coding CLIs rise, fork, and stumble over the past couple of years, I...
Machine Translation's Low-Resource Language Problem
There are roughly 7,000 languages spoken on Earth. Google Translate supports about 130 of them. Most commercial MT systems handle fewer than 30 well. If you...
State Space Models vs Transformers: A Practical Guide
Transformers won't be the only game in town for much longer. I know that sounds like a bold claim — we've all watched the transformer architecture dominate...
How AI Tools Are Quietly Changing the Way Developers Think
I noticed it about six months into using Copilot regularly. I was debugging a Python script and reached for the AI assistant before I'd actually read the error...
LLM Agents Are Just Distributed Systems
The AI community is building multi-agent systems — teams of LLMs that divide work, communicate, and collaborate to solve problems no single model can handle. A...
Beyond Self-Attention: What Comes After Transformers
The transformer architecture has been running AI for eight years now. Every major language model, most image generation systems, and an increasing number of...
Running Large Language Models on Your Own Hardware
Last year I spent $4,200 building a local inference rig that could run a 70B parameter model at reasonable speed. A colleague looked at my setup and asked the...