Know when to let the model cook
Taste is all that matters.
Jan 18, 2026·6 min read
Articles
50 articles on language models, agents, and software design.
AllAdviceAgentsApplied AIBraintrustClusteringComfyUIDebuggingDeploymentDiffusion ModelsDocumentationEvalsInstructorLLMsLangchainMCPMacModalPersonal DevelopmentPythonRAGRWKVReflectionsReinforcement LearningSFTSynthetic DataTestingUI GenerationUI/UXVoiceWalkthroughWhisper
How I Broke Into AI Without a Roadmap
The messy, fast-changing path that took me from front-end engineering to LLMs.
Jan 12, 2026·8 min read
Reversing Chinese Poetry
Creating our first RL Pipeline with Verifiers
Jan 2, 2026·22 min read·Reinforcement Learning From Scratch
Three Lessons I've Learned at Manus
Lessons learnt from going from zero to $100M ARR in 8 months
Dec 22, 2025·7 min read
Implementing BPE
Building a Byte-Pair Encoding tokenizer from scratch
Nov 30, 2025·34 min read·LLMs From Scratch
Spinning Up RL
Getting started with reinforcement learning
Nov 9, 2025·14 min read·Reinforcement Learning From Scratch
Agentic Search
Models can't do much without the right context, agentic search does just that
Oct 11, 2025·13 min read·Building an Agent
Building your own AI SDK
Switch between models with your own custom router
Oct 9, 2025·32 min read·Building an Agent
Building a Coding CLI with React Ink
Migrating Our Coding Agent to React Ink
Jul 17, 2025·18 min read·Building an Agent
Building An Agent
Implementing a coding agent in around 200 lines of Javascript code
Jul 16, 2025·13 min read·Building an Agent
MCPs for Tiny Automations
If you're not working with MCPs, you're missing out on a powerful tool for rapid prototyping and automation.
Jul 1, 2025·7 min read
Coding is the New Writing
Turns out I never liked coding all along
Jun 27, 2025·6 min read
Building Voice Agents with ElevenLabs Conversational AI
Lessons from building a voice-based chatbot for customer service training
Apr 22, 2025·7 min read
Why are voice agents hard to build?
Three key things making it tough to build reliable voice agents
Apr 20, 2025·4 min read
Why you're missing out on not building with streaming UIs in mind
Key considerations when building UIs that rely on streaming LLM content
Mar 25, 2025·6 min read
MCPs are really LLM microservices
How the Model Context Protocol is really just a precursor to LLM applications as microservices
Mar 8, 2025·8 min read
Building Reliable LLM Applications
How to build reliable LLM applications with structured outputs, synthetic data and binary metrics
Jan 27, 2025·11 min read
Understanding User Conversations
How do we understand Conversations at Scale while preserving user privacy?
Jan 4, 2025·20 min read
How I Use Claude
How do I use Claude on a day to day basis?
Jan 4, 2025·6 min read
Getting started with language models in 2025
A road map for 2025 and some thoughts on how to get started
Dec 29, 2024·13 min read
What Happened in 2024
A year of personal and professional growth
Dec 26, 2024·5 min read
A Weekend of Text to Image/Video Models
Practical guide to setting up text-to-image and video generation using Modal and ComfyUI
Dec 22, 2024·7 min read
Simplify your LLM Evals
A practical guide to writing binary evals for subjective tasks
Dec 15, 2024·7 min read
Is there value in a wrapper
Why infrastructure, user experience, and data create lasting competitive advantages in AI applications
Dec 14, 2024·7 min read
What it means to look at your data
Learn how to evaluate and improve your LLM systems
Dec 9, 2024·6 min read
Taming Your LLM Application
How to start shipping more reliable LLM applications to prod
Dec 5, 2024·14 min read
Are your eval improvements just pure chance?
Grokking simple statistical analysis for LLM evals
Dec 4, 2024·10 min read
What Makes Good Documentation
Lessons learnt from writing 40k lines of documentation of instructor
Dec 2, 2024·6 min read
Why User Intent matters the most for Synthetic Data
The easiest thing you can do today to improve your synthetic data quality
Nov 29, 2024·9 min read
You're probably using LLMs wrongly
Get 10x the results with LLMs in 3 simple steps
Nov 28, 2024·6 min read
A minimal setup guide for Mac
How I'm setting up my Mac for ML Open Source Development
Nov 27, 2024·4 min read
Write Stupid Evals
Keep it simple and worry about the rest later
Nov 26, 2024·7 min read
Is RAG dead?
RAG isn't dead, it just got more complicated
Nov 24, 2024·5 min read
Synthetic Data is no Free Lunch
Hard-earned lessons from generating millions of synthetic data points and why validation matters more than volume
Nov 23, 2024·8 min read
You're probably not doing experiments right
How to get the results that you want from your LLM experiments
Nov 20, 2024·5 min read
Why Instructor might be a better bet than Langchain
Deciding on the right LLM framework for your application
Sep 21, 2024·9 min read
How does Instructor work?
How your request goes from chat completion to validated Pydantic model
Sep 8, 2024·10 min read
Getting Started with Evals - a speedrun through Braintrust
Writing your first eval test in under 5 minutes
Sep 5, 2024·10 min read
How to create synthetic data that works
Lessons from generating a few million tokens of synthetic data with gpt-4o-mini
Aug 27, 2024·6 min read
AI Engineering World Fair
Some thoughts from the AI Engineering World Fair
Jun 30, 2024·6 min read
Grokking LLMs
Speedrunning everything I learnt in the past year
May 2, 2024·23 min read
Writing your first Rust cli Tool
A quick guide to creating tools for yourself
Apr 27, 2024·7 min read
Writing scripts that scale
A few actionable tips to writing better machine learning scripts
Apr 19, 2024·6 min read
Everything I've learnt about writing good Python code
Speedrun your way to becoming a good python developer and don't make the same mistakes I did
Apr 17, 2024·10 min read
Learning with Adult Responsibilities
Lessons from trying to teach myself about AI over the past 6 months
Jan 20, 2024·7 min read
GPT-React
Using RAG to generate UI Components
Dec 20, 2023·18 min read
A guide to RWKV V3
A guide to a strong open-source transformer alternative
Sep 28, 2023·13 min read
Reinventing Gandalf
How to simulate a red-team attack on your own models to improve their robustness
Sep 25, 2023·24 min read
Classifying Google Map locations with LLMs
Using LLMs to automatically tag and categorize your favourite eating spots
Jul 1, 2023·12 min read
Whispers In The Background
Implementing an Event-Driven approach for whisper transcriptions
May 1, 2023·4 min read