AIDevelopment
How to Build Agentic Graphs
A practical guide to designing agent graphs: parallelism, conflicts, model selection, and cache management, based on my painful but real experience with graphs over 4 months and 250k LoC shipped to prod.
Read →
AI
How to choose between GPT-5.6 Sol, Terra, and Luna + reasoning? Explaining practically using real-world examples.
I break down how to choose between GPT-5.6 models (Luna, Terra, Sol) and reasoning levels through a simple analogy with human attention: some tasks need more "memory for rules," others need more "time to think."
AIPersonal
Stop Babysitting Your Agents! Introducing Kent Workflows.
Explaining Kent Workflows - a new paradigm for working with agents that lets you turn manual agent management into a fully automated process where agents work in loops.
DevelopmentAI
Meet Kent 2.0 - Your Coding Accomplice
Released Kent 2.0 - formerly Builder, now Kent with a new site at kent.sh. This release includes: system prompt customization, new subagents with config examples, performance and terminal fixes, system sleep prevention, and more.
DevelopmentAI
I gave your agent access to Firefox - meet Firefox CLI
Firefox CLI is a CLI interface for controlling a real Firefox session with AI agents - a full equivalent of Agent Browser for Chrome, but better. Install once via an extension; supports Claude Code and Codex.
AIDevelopment
MCP is Deprecated
MCP has fundamental architectural problems - it pollutes context, kills flexibility, and creates security risks. For agents with terminal access, CLI is a far better alternative, and it's time to stop using MCP.
AIDevelopment
Claude-pilled: why complex agent workflows are working against you
Complex systems of agents, slash commands, and orchestrators aren't progress - they're micromanagement that gets in the way of frontier models doing their best work. Here's why the simple approach works better, and how I actually work.
AIDevelopment
How Does My Agent Survive 37+ Compactions in a Row? A Deep Dive into Proactive Compact in Kent
Explanation of Kent's advanced compaction algorithm and how it lets the agent run for dozens of sessions in a row without losing context or making unnecessary stops.
AIDevelopment
I got tired of every existing coding agent. So I built my own - Kent.
Introducing Kent - a free, open-source coding agent built for professional engineers. Outperforms Codex and is already available on GitHub.
AIPersonal
Gemini finally fixed, Google and Anthropic shot themselves in the foot, and OpenAI is farming karma - weekly news.
Google released Gemini 3.1 Pro with fixed tool calling, Anthropic and Google started aggressively banning subscription use outside their own tools, while OpenAI keeps actively supporting OpenClaw and is gearing up for GPT-5.3.
AIPersonal
I spent $150 and 5 days testing OpenClaw with all top models. My verdict on the future of AI assistants.
Spent 5 days and $150+ testing OpenClaw with different AI models. GPT is a robot without personality, Gemini has great character but can't work properly, Opus is perfect but costs $100/day. OpenClaw is still full of bugs (4000 issues, 3000 PRs).
AIPersonal
I've been using OpenClaw for a month now. Full review: what it is, why the hype, and whether you should try it
OpenClaw (formerly ClawdBot) by Peter Steinberger is a personal AI assistant with file-system access, background agents, and remote control. This post covers its origins, hype, and my hands-on take.
AIDevelopment
What are AI agent skills and how to use them - complete breakdown with examples
Agent skills are a way to progressively disclose context to AI through markdown files, which saves tokens and boosts performance. I explain why you need them, when to use them, how to create them, and debunk the myths.
AIPersonal
I No Longer Write or Read Code. AI Does It Better Than Me
In December, AI models crossed a threshold after which I became useless as a programmer. Now I push code to prod that Ive never read.
DevelopmentAI
Agents and Gradle Don't Get Along - I Fixed It in Two Commands
Introducing ksrc - a CLI utility that simplifies searching and viewing Kotlin library source code from 15+ commands down to two for your AI agents.
AIDevelopment
I spent 400 hours working with AI agents and found the best one - here it is.
Detailed comparison of Codex and Claude Code after three months of using both tools. Breaking down the pros and cons of each, model features, harnesses, pricing, and revealing who I paid $200/month to
AI
Anthropic discovered signs of consciousness in LLMs. New research on AI introspection
Anthropic published research showing that large language models are capable of detecting manipulations of their thinking process and recognizing their own intentions, which may indicate elementary forms of self-awareness.
AIPersonal
I Vibecoded a Blog in 8 Hours Without Writing a Single Line of Code
I built a complete blogging platform with automated publishing across multiple languages and channels in 8 hours, using Claude without writing a single line of code myself.
AIDevelopment
Claude 4.5 Sonnet Complete Review: Why Its Time to Forget About Opus
Claude 4.5 Sonnet is a breakthrough update that completely replaces Opus for most tasks thanks to better instruction following, parallel tool calls, and impressive speed. You can now work with lower limits and greater productivity.