Detailed documentation about my journey building my first LLM, from architectural implimentation, dataset engineering, training loop implimentation to instruction finetuning.
](http://karimbenboubaker.me/covers/ai-infrastructure-is-something-diffrent-cover.png)
AI workloads are forcing a fundamental shift in computing infrastructure, driving data centers back to integrated, mainframe-style systems optimized for massive bandwidth and sustained computation.
](http://karimbenboubaker.me/covers/plan-and-act-cover.png)
PLAN-AND-ACT is a novel AI agent architecture that significantly improves performance in complex, goal-directed tasks on the web by separating high-level planning from low-level execution and training both components with an innovative reverse-engineered synthetic data pipeline.
](http://karimbenboubaker.me/covers/cover-ai-coding-agents.jpg)
AI coding assistants enhance productivity by suggesting improvements, while AI coding agents aim for higher autonomy by reasoning about complex problems