# Q1 2026 Reading Syllabus A structured reading plan across four domains: classic literature, deep fiction, neuroscience, and applied engineering. *** ## Classic Literature *Goal: Understand writing philosophy, learn storytelling craft, build my own voice* 1. **Little Women** — Louisa May Alcott *(in progress)* * Craft focus: Character voice differentiation 2. **Pride and Prejudice** — Jane Austen * Craft focus: Irony, wit, free indirect discourse *** ## Deep Fiction *Goal: Immerse in great stories, become more creative and thoughtful* 1. **The Shadow of the Wind** — Carlos Ruiz Zafón * Craft focus: Atmospheric world-building, layered mystery, sensory prose *** ## Neuroscience *Goal: Understand how the mind functions, live better* 1. **The Brain That Changes Itself** — Norman Doidge * Focus: Neuroplasticity—how the brain rewires through experience Also reading: *Thinking Fast and Slow* by Daniel Kahneman *** ## Applied Engineering *Goal: Career growth in ML, NLP, and systems* ### Books 1. **Designing Data-Intensive Applications** — Martin Kleppmann 2. **NLP with Transformers** — Tunstall, von Werra & Wolf ### Anthropic Research Papers * Scaling Monosemanticity * Tracing the Thoughts of a Large Language Model * Towards Monosemanticity * Claude's Constitution * Alignment Faking in LLMs * Collective Constitutional AI *** ## Reading Approach * **Pacing:** Steady * **Parallel books:** 2-3 at a time (one per domain) * **Challenge tolerance:** High in expertise areas, accessible elsewhere ***

This syllabus was generated with reading-companion, an MCP server I built for personalized reading plans.

# Somya Anand Building AI systems inspired by human thinking—memory, dialogue, and learning through use. Curious about NLP, personalization, lifelong agents, and deeply human tools. This is my digital garden. If you’re exploring interesting problems in ML or AI, I’d love to [hear about them](./about.md#contact).
Current interests... Co-evolving AI systems Nia Project Finding my writing voice, bird by bird Reading big messy fiction
## Recent Writing **[The World is the Test](writing/2026-03-02-the-world-is-the-test/index.html.md)** Why evaluating AI agents requires building the worlds they'll inhabit. **[The Era of Personalized Software](writing/2026-01-22-the-era-of-personalized-software/index.html.md)** Building for an audience of one—how cheap implementation is enabling the long tail of software. **[From Reading Rut to Reading System](writing/2026-01-15-reading-rut-to-reading-system/index.html.md)** Building an LLM-powered book companion inspired by a Tokyo librarian. [Browse all writing >](./writing/)
## From the Garden **[Reading Companion](garden/reading-companion/index.html.md)** An MCP server for intentional reading and reflection. **[Q1 2026 Reading Syllabus](garden/reading-syllabus/index.html.md)** My current reading plan across four domains. **[AI Interviewer](https://interviews.somya.dev)** Adaptive interview system with persona-driven evaluation. **[Customer Intelligence](https://customer-intelligence-demo.streamlit.app/Pipeline_Demo)** Simulation-based evaluation for sales enablement. [Explore more >](./garden/)
## Books & Reading ### Reading Now * *Little Women* by Louisa May Alcott * *Thinking Fast and Slow* by Daniel Kahneman * *Designing Data-Intensive Applications* by Martin Kleppmann ### Up Next * *Pride and Prejudice* by Jane Austen * *The Shadow of the Wind* by Carlos Ruiz Zafón [View reading log >](./reading/)
# Writing Thoughts on AI, engineering, management, and the spaces where they intersect. *** ## 2026 **[The World is the Test](2026-03-02-the-world-is-the-test/index.html.md)** *(March 2, 2026)*\ Why evaluating AI agents requires building the worlds they'll inhabit—lessons from disaster science, self-driving, and agent-based modeling. **[The Era of Personalized Software](2026-01-22-the-era-of-personalized-software/index.html.md)** *(January 22, 2026)*\ Building for an audience of one—how cheap implementation is enabling the long tail of software. **[From Reading Rut to Reading System](2026-01-15-reading-rut-to-reading-system/index.html.md)** *(January 15, 2026)*\ Building an LLM-powered book companion inspired by a Tokyo librarian who always knows the right book. **[Why I Read Fiction](2026-01-11-why-i-read-fiction/index.html.md)** *(January 11, 2026)*\ How fiction restored my attention and became a way to study storytelling without turning it into a task. **[Co-evolving AI Systems](2026-01-10-co-evolving-ai-systems/index.html.md)** *(January 10, 2026)*\ Building AI systems that evolve alongside their users through context, memory, and adaptation at inference time. ## 2025 **[Evaluating Work in the Age of AI](2025-12-10-evaluating-work-age-of-ai/index.html.md)** *(December 10, 2025)*\ Why clarity matters more than ever, and how to bring AI-shaped work into performance conversations. **[Using an LLM as a Rubber Duck for Ideas](2025-11-18-llm-rubber-duck/index.html.md)** *(November 18, 2025)*\ One of their most underrated uses is in the earliest stage of engineering projects. **[I Stepped Away](2025-10-31-i-stepped-away/index.html.md)** *(October 31, 2025)*\ Growth doesn't always mean moving forward — sometimes it means standing still. **[Rewiring My AI Mindset](2025-07-26-rewiring-ai-mindset/index.html.md)** *(July 26, 2025)*\ How AI Engineering by Chip Huyen helped me connect the dots and build better. **[My Experience Building a People-First Team](2025-07-02-building-people-first-team/index.html.md)** *(July 2, 2025)*\ Lessons from three years of leading applied scientists with curiosity, trust, and tailored growth. ## 2021 **[Lifecycle of a Bug](2021-06-05-lifecycle-of-a-bug/index.html.md)** *(June 5, 2021)*\ Debugging ML projects: sources of bugs and strategies to avoid them. ## 2020 **[Data to Text Generation Using SimpleNLG](2020-12-08-data-to-text-simplenlg/index.html.md)** *(December 8, 2020)*\ A hands-on tutorial for converting data to natural language using SimpleNLG. **[Why Are Code Reviews So Important?](2020-08-04-code-reviews/index.html.md)** *(August 4, 2020)*\ Best practices for effective code reviews, from understanding intent to appreciating feedback. **[What Did I Learn in 2019?](2020-01-13-what-i-learned-2019/index.html.md)** *(January 13, 2020)*\ Reflections on growth, leaving MindTickle, and starting fresh in a new country. ## 2017 **[Smart Fare Calendar System](2017-09-15-fare-calendar-system/index.html.md)** *(September 15, 2017)*\ Using clustering algorithms to categorize airfares for better price variation insights. **[Fare Trends](2017-09-01-fare-trends/index.html.md)** *(September 1, 2017)*\ Fare analytics and visualizations for hassle-free airline booking. **[Supervised Approach for Nuclei Segmentation](2017-08-11-supervised-nuclei-segmentation/index.html.md)** *(August 11, 2017)*\ A supervised approach for nuclei detection using pixel-wise and patch-wise information. **[Role of Emotions in Online Communities](2017-08-11-agent-based-modelling/index.html.md)** *(August 11, 2017)*\ Analyzing emotional expression in online communities using agent-based modeling. **[Y2038 Issue in Linux Kernel](2017-08-01-y2038-problem/index.html.md)** *(August 1, 2017)*\ The Year 2038 problem and contributions to fixing it in the Linux kernel. **[Fare Alert System](2017-05-12-fare-alert-system/index.html.md)** *(May 12, 2017)*\ Designing a fare monitoring system to notify users of significant airfare changes. **[User Classification](2017-03-11-user-classification/index.html.md)** *(March 11, 2017)*\ Classifying travel marketplace users by their likelihood to book. ## 2016 **[Coccinelle](2016-08-11-coccinelle-usages/index.html.md)** *(August 11, 2016)*\ A beginner-friendly guide to using Coccinelle for C code transformations in the Linux kernel.