Tutorials & Guides
A Bayesian analysis of the Monty Hall problem shows how observing a host's behavior can probabilistically determine the optimal strategy.
Explains Simpson's paradox through statistical charts showing how combining data can reverse apparent trends.
Explains how Chain of Thought prompting techniques from AI can improve human problem-solving and communication in technical interviews.
Simon Willison shares a JavaScript technique using document.currentScript to create inline templates that replace themselves with dynamic content.
LessWrong shares practical tips for managing multiagent systems with Claude Opus 5.5, emphasizing professional communication between subagents and avoiding manager agent bottlenecks.
Author built a claim-checker tool using Codex that incorrectly passed a wrong claim, revealing limitations of rule-based AI verification systems.
Part 1 of a guide on deploying data science code across different environments and platforms.
Testing shows pasting full chat history costs 20-31x more than lookup methods with no performance benefit for AI memory.
Data scientists need software engineering principles to build AI applications that can evolve, especially as AI agents write code.
Hugging Face is hosting a livestream teaching developers how to achieve significant speed-ups in local LLMs using speculative decoding techniques.
Frontier AI models increasingly incorporate users' public online writings into prompt context, requiring awareness and proactive management.
A developer jailbroke an unused Kindle using GPT-6 Astra to create a photo slideshow app, detailing the technical process of building custom tools called KindleCTL.
Geoffrey Huntley shares a technique using pre-commit hooks to enforce AI coding agents to use custom diagnostics libraries instead of direct observability calls.
A deep dive into 6 advanced architectural patterns for building production-ready agentic systems, covering context engineering and multi-agent workflows.
Developer shares insights from using AI agents (Claude, Codex) to decompile a first-person shooter game over 3 months, focusing on orchestration and infrastructure optimization.
A guide to applying NLP techniques like classification, topic modeling, and embeddings to product data science problems such as churn prediction and customer analysis.
Simon Willison built a new blog newsletter feature entirely using voice conversation with GPT-6 Astra High while cooking dinner.
A programmer shares a 'Kobayashi Maru' style interview question designed to reveal a candidate's decision-making process through difficult trade-offs rather than a single correct answer.
OpenAI's Decisions API provides fast classification and decision-making endpoints for applications needing typed responses with confidence scores.
A developer shares their process for creating custom language models using HuggingChat's ML-interm feature, training a Qwen-based prompt rewriter from 9B to 0.8B for $16, with detailed prompting strategies.
OpenAI released a practical guide for developers on migrating to the Responses API, designing agents, and tuning prompts for GPT-5 models.
OpenAI published a practical guide covering AI agent design, orchestration, deployment, use cases, model selection, tool design, and multi-agent patterns.
The dual-LLM pattern secures AI agents by separating privileged and quarantined LLMs to prevent prompt injection attacks when reading untrusted sources.
A Verge reviewer documents their journey experimenting with local AI models on high-end hardware, exploring privacy benefits and practical challenges of running LLMs locally.
OpenAI demonstrates how to use ChatGPT's canvas feature to convert product requirements into functional HTML/React prototypes.
OpenAI shares how its engineering teams use Codex for code understanding, system refactoring, performance optimization, and workflow acceleration.
Step-by-step tutorial shows how to build a simple AI agent that uses an LLM to call Python functions for database queries.
OpenAI demonstrates how ChatGPT can directly push generated code to IDEs to accelerate developer workflows.
OpenAI demonstrates how ChatGPT can plan, search, read sources, and compile detailed market research reports to support analysis.
OpenAI shares internal use cases and workflows for ChatGPT Atlas in a webinar demonstrating practical enterprise applications.