The refusal problem in large language models
July 29, 2025 │ ai
Can small AI models think as well as large ones?
July 27, 2025 │ ai
What kind of work I want (in 2025)
Do not yell at the language model
July 24, 2025 │ ai
The case for regulating AI companions
July 19, 2025 │ ai, ethics, alignment failures
Vibe coding and the silent AI war inside tech companies
July 17, 2025 │ ai, tech companies, leaddev
How to actually use Model Context Protocol
July 17, 2025 │ ai, explainers, mcp
Practical notes on getting LLMs to generate new ideas
July 15, 2025 │ ai
The three great virtues of an AI-assisted programmer
July 14, 2025 │ ai
Building an RTS where you issue orders to AI agents
July 14, 2025 │ ai, side projects
METR's AI productivity study is really good
July 11, 2025 │ ai
Why we should anthropomorphize LLMs
Mecha-Hitler, Grok, and why it's so hard to give LLMs the right personality
July 9, 2025 │ ai, alignment failures, ethics
How I use LLMs to learn new subjects
July 8, 2025 │ ai
The more senior engineers get, the more results matter
July 8, 2025 │ tech companies, staff