Boris Cherny shares his experience using Claude Code + Opus 4.5 to write all code for 259 PRs in a month, highlighting AI's coding progress.
A developer reflects on the anxiety and impact of using Large Language Models (LLMs) in programming, balancing skepticism with practical utility.
A software engineer shares practical strategies for effectively using AI coding agents like Claude Code, emphasizing setup and feedback loops.
An introduction to mutation testing, a technique for evaluating the quality and trustworthiness of automated test suites by deliberately injecting faults.
Testing GPU performance on a Raspberry Pi 5 versus a desktop PC for transcoding, AI, and multi-GPU tasks, showing surprising efficiency.
A visual essay explaining LLM internals like tokenization, embeddings, and transformer architecture in an accessible way.
![[notes] Some of Us Actually Like Coding](https://alldevblogs.blob.core.windows.net/thumbs/article-2d50f68bf2fa-full-8b7d93d2.webp)
A software engineer's perspective on enjoying coding amidst the rise of AI coding agents, arguing for the value of hands-on programming.
Google releases Gemini 3 Flash, a faster, cheaper AI model with strong coding and multimodal capabilities, compared to previous versions.
Explains why large language models (LLMs) like ChatGPT generate factually incorrect or fabricated information, known as hallucinations.
A developer explains their switch from ChatGPT to Claude for coding and technical work, citing Claude Code's effectiveness and personal preferences.
Explores the 'Normalization of Deviance' concept in AI safety, warning against complacency with LLM vulnerabilities like prompt injection.
Using LLMs to analyze and grade the accuracy of decade-old Hacker News discussions with the benefit of hindsight.
Mistral AI releases Devstral 2 and Devstral Small 2, two new open models focused on powering coding agents and software development tasks.
An interview about Canada Spends, a project using Datasette, SQLite, and LLMs to make Canadian government financial data accessible and explorable.
A blog post analyzing a critical bug in Claude Code where a command accidentally deleted a user's home directory.
AI is predicted to bring formal verification tools like Dafny and Verus into mainstream use, aided by LLMs making them more accessible.
Bryan Cantrill discusses applying Large Language Models (LLMs) at Oxide, evaluating them against the company's core values.
Tips from David Crespo on effectively using Claude Code for understanding codebases and automating tedious coding tasks.
Explores advanced Context Engineering techniques for AI agents, focusing on combating Context Rot and improving multi-agent coordination.
