llm4 articles

LLMApril 27, 2026
The Open-Weights Models You Can Actually Download
A snapshot of who's shipping what in open-weights LLMs right now: parameter counts, architecture, context length, license, and whether the weights are really open or just open with friction.
11 min readRead →

LLMMarch 21, 2026
How Much Should You Trust What an LLM Tells You?
I fine-tuned a model on 50 wrong answers to see what it does with a question it hasn't seen. The result changed how I think about trusting AI.
25 min readRead →

AI AgentsMarch 7, 2026
You Probably Don't Need an AI Agent
Everyone's throwing LLMs at problems that don't need them and calling everything an agent. Here's a simple way to think about what goes where.
5 min readRead →

LLMMarch 5, 2026
What Even Is AI Right Now
A no-hype look at where AI actually stands in 2026. What's real, what's noise, and what matters if you're building things.
15 min readRead →