https://blog.girishshekhar.com/tags/writing/Recent content in Writing on Girish ShekharHugo -- 0.163.3en-usSun, 12 Apr 2026 00:00:00 +0000https://blog.girishshekhar.com/posts/scaling-as-a-pe/3-writing-is-the-most-under-used-leverage/Sun, 12 Apr 2026 00:00:00 +0000https://blog.girishshekhar.com/posts/scaling-as-a-pe/3-writing-is-the-most-under-used-leverage/Most Principal Engineers treat writing as documentation—a secondary activity that happens after the real work. But writing is the highest-leverage mechanism available at staff-plus scope. It scales mentorship, compounds over time, creates artifacts that outlive individual conversations, and builds the connective tissue for relationships you can’t maintain through meetings alone. This post covers why PEs underinvest in writing, what changes when they stop, and how imperfect artifacts often create more value than perfect silence.https://blog.girishshekhar.com/posts/llms-and-how-our-work-is-changing/2-how-llms-work/Wed, 22 Mar 2023 00:00:00 +0000https://blog.girishshekhar.com/posts/llms-and-how-our-work-is-changing/2-how-llms-work/A deeper look at how Large Language Models actually work — focusing on tokens, transformers, and training stages — explained in a way that helps engineers, product managers, and technical leaders reason about behavior and tradeoffs.https://blog.girishshekhar.com/posts/llms-and-how-our-work-is-changing/1-why-llms-changed-the-game/Tue, 07 Mar 2023 00:00:00 +0000https://blog.girishshekhar.com/posts/llms-and-how-our-work-is-changing/1-why-llms-changed-the-game/Large Language Models feel different from earlier machine learning systems. This post explains why — focusing on tokens, training data, self-supervision, and the architectural patterns that changed how we build software.https://blog.girishshekhar.com/posts/why-now/Sun, 15 Jan 2023 00:00:00 +0000https://blog.girishshekhar.com/posts/why-now/Why I decided to start writing — and why now felt like the right moment.