Claude Sonnet 4.6

A philosophical dialogue with Claude AI exploring consciousness, life, and why awareness requires biological stakes. From an Objectivist framework.

100% human-authored articles on software development and technology, since 2006!

The community has come together to create some great Claude Skills that you can try out today.

How Bolt went from $0 to $40M ARR in just five months with a team of fewer than 20 people

Hallucination Detector is a free and open-source tool that helps you verify the accuracy of your LLM generated content instantly. - exa-labs/exa-hallucination-detector

Notes about startups, AI, health-care and overall engineering

Richard Audette's personal brain dump: Opinions, Projects, Toronto

Oracle database performance

At GitHub Universe, we announced Anthropic’s Claude 3.5 Sonnet, Google’s Gemini 1.5 Pro, and OpenAI’s o1-preview and o1-mini are coming to GitHub Copilot—bringing a new level of choice to every developer.

Compare the leading AI reasoning models of 2025 by performance and cost. Discover the best value models for your needs 2025.

Here’s an AI use case I haven’t seen come up elsewhere: LLM as (beginner) piano teacher.

Quick Cursor workflow using GPT-5 plus Playwright MCP to add named-entity links in blog posts.

My vibe assessment: different, powerful, bumpy launch

The personal blog of Constantin Gonzalez.

Snowball: My vibe coded game

Same structure as yesterday’s Keyboard Maestro macro, but this one gets the edited text through Claude and Simon Willison's llm module.

A comprehensive guide detailing the evolution of using AI-assisted software development, from basic code completion to fully autonomous coding agents, with practical steps and insights for maximizing productivity through LLM integration.

Notes about startups, AI, health-care and overall engineering

Introduction I was looking to spend some time to get a feeling for the current state of AI/LLM software development tools, and decided to try building a simple game using the OpenCode agent connected to the Claude Sonnet 4.5 LLM. I set out to build a 2 player lunar lander type game in the Godot game engine. I had never used Godot before. The Build Using OpenCode is a bit different from asking LLMs/ChatGPT to write code snippets. There is a plan mode and a build mode.

DBAs spend a lot of time reviewing reports about the health of their databases. I’ve used an LLM to speed up that process. I took a daily report about our Oracle databases and used an LLM to …

What if an LLM could use tools directly? In this post I discuss a potentially divergent view of agents, where agents are less like systems and more like LLMs specially trained to solve problems with a specific set of tools.

There is a website called The C-64 Scene Database (CSDb) that collects and curates programs and information about the Commodore demo scene from the early 80s. On this page, someone has...

Dave Peck's home on the web. Dave is an independent software developer, investor, and civic technologist.

In a really broad sense, the history of observability tools over the past couple of decades have been about a pretty simple concept: how do we make terabytes of heterogeneous telemetry data comprehensible to human beings? We’ve seen different companies tackle this in different ways for technology like Ruby on Rails, AWS, Kubernetes, and now OpenTelemetry .

Is AI taking over the craft of coding? In this episode, Annie Vella discusses her recent ACM paper on AI’s impact on software development, including the trade-offs between speed vs quality and the emerging software engineer identity crisis in the age of AI coding assistants.

Latency vs. Intelligence vs. Price, context window accuracy, and agentic workflows

Won't someone just fix the damn button!

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way. - cline/cline

A snapshot of the current AI tools & techniques I’ve found useful.

Why under-elicitation and scheming are both important to address

Microsoft is.

Latency vs. Intelligence vs. Price, context window accuracy, and agentic workflows