Pick Your Fights: A Pragmatic Approach to Coding with AI
Parents learn to "pick their fights," understanding that not every small disagreement warrants a battle. This wisdom translates remarkably well to the realm of…
Read postAll LLM posts
Everything in this archive, newest first.
AI in 2025: Two Major Shifts
The ability to train competitive AI models at 1/45th the traditional cost is fundamentally changing who can develop AI systems and what they can…
Read postDeepSeek and the Effects of GPU Export Controls
Last week, DeepSeek unveiled their V3 model, trained on just 2,048 H800 GPUs - a fraction of the hardware used by OpenAI or Meta.…
Read postTrae AI IDE: ByteDance’s Answer to Cursor
ByteDance recently launched Trae, a new AI-powered IDE that's generating buzz in the developer community. As someone who has extensively analyzed various AI coding…
Read postCursor is Anthropic’s Largest Customer (and Maxing Out Their GPUs)
Cursor is Anthropic's Largest Customer and is apparently hitting the limits of what their GPU infrastructure can handle....Read More...
Read postAI Tools Are Making Developers Stronger, Not Obsolete
There's a lot of discussion lately about whether AI and large language models (LLMs) will replace software engineers. While AI is certainly transforming how…
Read postAI Content Is Great – You’re Just Using It Wrong
People often talk about AI-generated content as if it's all the same thing. It's not. There are two very different ways to use AI…
Read postWTF is Agentic AI?
There's been a lot of noise lately about "agentic AI," with everyone from startups to tech giants claiming it's the next big thing. But…
Read postClaude’s Quality is Dropping – Here’s Why
Claude's performance has taken a noticeable hit lately. I've been using it daily for several months, and the degradation is pretty clear. Let me…
Read postLaravel Command to Generate Database Schema Documentation for LLM Prompts
When working with Large Language Models (LLMs) like ChatGPT or Claude to help with Laravel development, you often need to share your database schema…
Read postThe New Claude 3.5 Sonnet is Lazy When Given Large Context
I've noticed a significant issue with Anthropic's latest Claude 3.5 Sonnet model: it becomes increasingly lazy as conversation context grows. This is a consistent…
Read postCopilot vs Cursor vs Cody vs Supermaven vs Aider
I used GitHub Copilot from early 2022 to mid 2024 and switched to Cursor at the beginning of 2024. I've tested Sourcegraph Cody and…
Read post