Explores how AI boosts coding speed but highlights alignment as the true bottleneck in software development.
A humorous anecdote about an AI-generated image of a horse riding an astronaut on a pelican on a bicycle, with a self-added sign.
A developer reflects on how AI makes the slow, deliberate process of learning and problem-solving feel shameful.
Explores the exact closed-form solution to the nonlinear pendulum equation using Jacobi elliptic functions, comparing it with numerical and linearized solutions.
Summary of the Antithesis BugBash Conference 2026, covering software verification, distributed systems, formal verification, and test coverage talks.
Explores the formula for the nth derivative of a quotient, a lesser-known counterpart to the product rule.
Visualizing NYC subway hourly flows with 424 pie charts, breaking data visualization rules using MTA origin-destination data.
Simon Willison quotes Romain Huet on OpenAI's GPT-5.5 unifying Codex and main model for agentic coding.
A quote from Romain Huet confirming OpenAI won't release a separate GPT-5.5-Codex model, as coding capabilities are unified.
Tutorial on automating MEV analysis on EVM chains using mevlog-rs MCP and OpenClaw agent for blockchain querying.
Developer creates Excaliclaw, an OpenClaw skill for generating Excalidraw diagrams, detailing setup, debugging, and final working patterns.
A voice transcript conversation about David Deutsch's knowledge theory and the PAI algorithm for personal AI infrastructure.
Guide to prompting GPT-5.5 with tips from OpenAI, including migration advice and a trick for multi-step tasks.
A guide on prompting GPT-5.5, including tips for multi-step tasks, migration advice, and starting fresh with new prompts.
Vim tip explaining that the substitute command delimiter doesn't have to be a slash, allowing easier handling of paths and URLs.
Analysis of Bloomberg's 2024 report on John Ternus as Tim Cook's likely successor at Apple, with commentary on CEO transition claims.
Challenges the traditional test pyramid, advocating for more integration tests over unit tests using modern tools like Testcontainers.
A developer shares how AI now writes 97% of their production code, detailing workflow changes and lessons learned from using Cursor agents.
Release notes for llm 0.31, a command-line tool for accessing large language models, featuring GPT-5.5 support and new options.
Release notes for llm 0.31, a command-line tool for accessing large language models, featuring GPT-5.5 support and new options.
