Writing

Essays on coding agents, LLM systems, MCP, and AI security. All posts live at Shrivu's Substack — subscribe there or via RSS.

2026

2026-08-17 — How I use AI in 2026 (Coding, Writing, Learning, Assistant-ing)
A personal update to "How I use AI (2025)".
2026-08-10 — Exploring Claude/GPT Knowledge Cutoffs & Pre-training Timelines
An analysis of what models know and what it tells us about how they were trained.
2026-06-13 — Designing Software for Software Factories
Reflections on turning software engineering into agentic loops.
2026-05-10 — How AI Productivity Fails
Why we are not actually 10x more productive (yet).
2026-05-04 — Nora, Our First Agent Employee
How a Slack bot grew into the agent platform that runs Abnormal.
2026-03-29 — The Transposed Organization
How AI drives companies to reorganize around loops, not functions.
2026-03-02 — Our Design Docs Write Themselves
How markdown files, a Zoom bot, and the Claude Code SDK replaced our design review cycle.
2026-02-16 — Taste Is Not a Moat
Why the last human edge is already being industrialized.
2026-01-25 — Move Faster
Why speed matters and why it's more than just timing.
2026-01-18 — Building Multi-Agent Systems (Part 3)
Updated methods for scaling scripting-based agents to handle complex problems reliably.
2026-01-10 — Most Code is Just Cache
As personal apps become trivial, we should stop thinking of code the same way.

2025

2025-12-21 — Understanding AI Benchmarks
Tips for interpreting frontier model releases and their SOTA benchmark scores.
2025-11-02 — How I Use Every Claude Code Feature
A brain dump of all the ways I've been using Claude Code.
2025-08-24 — Betting Against the Models
Speculations on the future of cybersecurity products for AI agents.
2025-08-17 — AI Can't Read Your Docs
Designing software that today's AI coding agents can actually use.
2025-07-19 — Assistants Aren't the Future of AI
Speculations on what comes after (or instead) of AI assistants.
2025-07-05 — Building Multi-Agent Systems (Part 2)
Updated methods for scaling LLM-based agents to handle complex problems reliably.
2025-06-28 — How to Train Your GPT Wrapper
Improving your agents automatically with experience.
2025-06-08 — How I use AI (2025)
Some thoughts on using AI for everyday things.
2025-05-04 — How to Stop Your Human From Hallucinating
When humans sometimes act like confused language models.
2025-04-13 — Everything Wrong with MCP
Explaining the Model Context Protocol and everything that might go wrong.
2025-03-16 — How Cursor (AI IDE) Works
Turning LLMs into coding experts and how to take advantage of them.
2025-03-01 — Working with Systems Smarter Than You
Some opinions on what the future might look like for jobs, AI, and software engineering.
2025-02-08 — How to Backdoor Large Language Models
Making "BadSeek", a sneaky open-source coding model.
2025-01-27 — Socioeconomic Modeling with Reasoning Models
Using a complex political simulation game to test state-of-the-art reasoning models.

2024

2024-12-26 — Building Multi-Agent Systems
Scaling LLM-based agents to handle complex problems reliably.
2024-11-24 — Building v0 in a Weekend
Building a prompt-to-site app in 48 hours using AI.
2024-10-21 — AI-powered Software Engineering
Scaling software development at the pace of AI.
2024-03-30 — Terrain Diffusion
Paint infinite landscapes using diffusion models.
2024-03-03 — Infinite Alchemy
Building an infinite crafting game using LLMs and DALLE.

2023

2023-11-23 — Speculations on Building Superintelligence
Predictions on superintelligent AI based on what we know in 2023.
2023-10-27 — Large Multimodal Models (LMMs)
How large language models "read" text and how we can adapt them to non-text inputs.
2023-10-08 — AI-powered Cyberattacks
What could cyberattacks look like with advanced generative AI capabilities?
2023-09-25 — Detecting ChatGPT Online
Can you tell if text is generated by ChatGPT?

Machine-readable: llms.txt · sitemap · projects.json · blog RSS