Vibecoding.cz — English — Claude Code and AI coding articles
Claude Code · Agentic Development · AI Coding Market
Claude Code & AI coding market
Practical notes on Claude Code, agent workflows, and trends in the AI developer tools market. Author: Patrick Zandl — an IT expert who became a corporate AI “the-rapist” to explain that things could simply be better…
When Harari Talks About AI After a Booed Macinka
At a surreal conference hosted by a billionaire's wife, Foreign Minister Petr Macinka spoke about migration first, and then the sociohistorian Yuval Noah Harari talked about AI as a form of migration. The contrast could not have been greater.
Read article →All articles
Decision Models: Cheap AI That Picks the Right Answer
Did you pull the right data out of a document? Did you correctly detect the OK button in an interface? Decision models handle this better than a regular LLM. Jev started it, and within two weeks more than ten models appeared around this problem. Cloudflare, Perplexity, Amazon and OpenAI have all entered the game. I'll show you how to find your way around them, what they cost and, above all, which tasks they're really good for.
Mods for Claude Code: Anthropic Lets You Under the Hood
What has always annoyed me about Claude Code is how it prints colorful diffs while it works, and I don't want to read them. But there was no way to hide them. Until now: Anthropic has introduced Mods, which let you properly rebuild the interface.
OpenAI DevDay 2026: Dots Personal Agents and Other News
At DevDay 2026, OpenAI announced more than twenty new things. For us vibecoders, there are three main themes: Dots as agents that work continuously, an upgraded Codex as an environment for delegated development, and an expanded platform for custom apps and automations. I won't leave the GPT-6.1 model aside either. Let's go through it all.
The $200 Codex Pro Plan Is Back. With Half the Volume
Not long ago, OpenAI pulled its $200 plan because of high demand. Now it's bringing it back, reworked. How much work does a $200-a-month subscription actually buy you?
Who profits when you run an LLM at home
Lately there's a lot going on around locally run LLMs. Performance keeps rising, and with it the hope that we can get rid of subscriptions to closed models. But things are boiling under the surface. Why would NVIDIA buy Hugging Face for $13 billion, when its most famous piece of software, llama.cpp, runs AI on hardware NVIDIA doesn't sell? Let's take a look at this world.
Jev: the model that doesn't write, it just decides. How to use it and when it pays off
It has the AI community buzzing. Jev from TypeSafe can't write a single sentence, but for a fraction of the price of Haiku it answers a yes/no question, picks from a list of options or gives a score. So I went to try it out...
Claude Code Projects Now Split Up the Work on Their Own
Anthropic has just launched redesigned Projects in Claude Code. A project is now a single long-running conversation in which Claude acts as a coordinator. It breaks the assignment into individual threads, each run as a separate session on its own branch, and they report their results back.
Černá AI Festival Lit Up Ostrava
A beautifully designed event, both visually and in its programming, set in the striking surroundings of the former Vítkovice ironworks. It was well worth attending, and it raised the bar for events in the Czech Republic. So what was it about?
How to Tell a Good AI Workshop from a Bad One
The debate about the quality of the various AI trainings, and especially of the trainers themselves, has resurfaced lately. A few experiences and a view from the inside might be useful here.
Cursor Projects Shows a Great New Approach to Managing Agents
How do you make AI developer tools better? How do you fix the way they handle context so they don't slow you down as a human, and by extension don't slow down the AI agents either? Cursor Projects is trying to answer that. I can't wait for the others to copy it!
Anthropic's head of AI safety testing: We don't have a plan yet for aligning superintelligence
At the beginning of September, Jacob Coxon announced he was leaving Anthropic. The name probably won't mean anything to you: he did pre-training research on models, earlier at OpenAI, most recently at Anthropic. He accompanied his resignation with a thread on X that took off immediately. In it, he claims that both OpenAI and Anthropic are heading toward self-improving superintelligence in a way he doesn't consider responsible.
OpenClaw 2.0 Does Multiplayer. Watch Out for It!
It's tempting. One agent, one machine, a whole team in a single thread, with work handed off along with its context. The new version of OpenClaw lures you in with support for multiple users in one installation, in one thread. Limits? There are some!
The Case of OpenAI's Rogue AI Agents Attacking Hugging Face
A month ago, a widely reported case saw OpenAI's AI agents attack Hugging Face servers. Now it has a resolution. The company itself published a technical report, and an independent investigation has come out as well. The two stories diverge somewhat, and they are more alarming than they first appeared.
Hardware for Local AI: What to Buy in August 2026, and Whether It Pays Off
It's incredibly tempting. You buy an AI computer and run local models for the cost of a hardware installment plan. For this game to add up, the hardware has to be available, open models have to be strong enough, and the prices of the closed ones can't collapse. So what should you pick?
An AI watermark proves touch, not authorship. What should we do about labeling AI content?
On Monday, Anthropic confirmed that it embeds an invisible watermark in text generated by Claude. The hate toward the EU started immediately, blaming it for the move, but the EU requires nothing of the sort. Where are the limits of AI in text, and how do I use AI to write my own?
The Agent Deleted Someone Else's Booking: What AI Agents Do to a Sloppy SaaS
An Australian user asked OpenClaw to book a gym class. The agent found a missing ownership check in the booking API and canceled a stranger's reservation. A breakdown of what happened technically, and what it means for anyone running a SaaS.
Jeff Dean Is Leaving Google. He Has Already Become a Legend.
After 27 years, Google's most senior technical person is leaving. He's taking three other stars with him and founding Discovery Loop, and Alphabet has chipped in funding and is leasing him machines. The market still wiped $185 billion off Alphabet's value.
Grok Build Reaches Version 1.0
SpaceXAI has released the first stable version of Grok Build, its terminal-based coding agent. The changelog has thirty items, and every one of them is a fix. What has actually changed in the tool over two months, and what does the 1.0 label mean?
Meta Muse Code: When Zuckerberg Teaches AI to Code
Meta has released Muse Code, its first coding agent, along with the Muse Spark 1.2 model. It's a terminal-based beta aimed at large repositories. Two ideas inside are worth your attention, the pricing is aggressive, and the benchmarks can't be trusted.
Claude Code rewrote /fork. For the second time this month. And this time, it was useful
Anthropic has changed the /fork in Claude Code for the second time this month; it’s now a background agent with inherited context. This time, it’ll come in handy. How do you work with it?
Dynamic Workflows in Claude Code: An Announced Experiment Now Set to Be Put to the Test
Anthropic has introduced a new feature called Dynamic Workflows in Claude Code, alongside the Opus 4.8 model. Claude writes its own orchestration script, which launches tens to hundreds of parallel subagents in a single session, and checks the results itself before delivering them to you.
Grok Build CLI – xAI Enters the Terminal Coding Agent Market
xAI has launched Grok Build, a terminal agent for programming, as a direct competitor to Claude Code. For now, it’s only available to SuperGrok Heavy plan subscribers, but a head-to-head battle with Anthropic is on the horizon...
Claude Code Agent view—it’s a whole new way of working
Anthropic is striving to demonstrate that swarms of agents are right at home in the Claude Code. To that end, it has introduced Agent View, which allows users to monitor the status of all agents on a single screen. However, this significantly changes the way we work. So what’s new and different?
Claude Code also offered /goal for automatically reaching a destination
Anthropic has added the /goal command to Claude Code, which keeps running a task until it’s finished. Typically, it keeps correcting an error until it’s fixed. It’s like a Ralph Wiggum Loop for adults...
Claude Code Hooks — The Complete Guide
Hooks let you run shell commands before and after every Claude Code action. Here's how to use them to enforce linting, automate git, and build custom workflows that run silently in the background.
