A developer's personal journey through a difficult year leads to insights on how AI is transforming software development and enabling the rise of the micro-entrepreneur.
A blog post quoting Armin Ronacher on how AI-assisted programming removes the frustrating labor of coding, leaving the core thinking intact.
A 2025 year-in-review analysis of large language models (LLMs), covering key developments in reasoning, architecture, costs, and predictions for 2026.
A 2025 year-in-review of Large Language Models, covering major developments in reasoning, architecture, costs, and predictions for 2026.
A curated list of notable LLM (Large Language Model) research papers published from July to December 2025, categorized by topic.
A curated list of notable LLM research papers from the second half of 2025, categorized by topics like reasoning, training, and multimodal models.
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.
