Vibecoding.cz — English — Claude Code and AI coding articles

Patrick Zandl on Claude Code, coding agents and the AI developer-tools market.

Recent

Article Claude Fable 5.2 is the smartest again. But Opus is enough for most of you Fable 5.1 cost twice as much as Opus 5.5, and in independent benchmarks it still fell short of it. The new version is fortunately in a different place: six points above Opus, a fifth cheaper, and faster than its predecessor. Even Anthropic itself advises starting with Opus, though. So when does it make sense to pay extra for Fable? Nov 9 · 13 min read Article Muse Ember: Haiku-level performance at a third of the price, but only for routine work Meta has released a cheap model that matched Claude Haiku 5.5 in an independent index, with tasks costing a third as much. What should you use it for, what should you test it on, and when should you stick with Haiku, DeepSeek or Luna? I tested it! Nov 9 · 7 min read Tutorial Sessions in Claude Code Can Talk to Each Other Do you have three Claude Code sessions open and keep copying output from one into another? You don't have to. Sessions can send messages to each other, and Claude can figure out on its own when it should. The feature has been in Claude Code since August, but a lot of people are only learning about it from a viral tutorial that is mostly made up. Let's go over where and how it actually works. Nov 4 · 7 min read Tutorial How Claude Code Handles Memory About Your Project You correct Claude on the same thing for the second time and wonder whether it will remember it this time. Claude Code now has two layers of persistent memory: rules that you write, and notes that it keeps on its own. Both are plain Markdown files on your disk. That is the biggest advantage of the whole approach and also its weakness, because a note in a file only helps if Claude remembers to open it. How do you work with this so that you end up satisfied? Nov 2 · 8 min read Article Gemini 4 Carbon has caught up with Opus, but you can't use it yet After a year, Google is back at the top of the independent Artificial Analysis leaderboard, and on the Vals Index it matches Claude Opus 5.5 at a third of the price. If you want to try it right now, you're out of luck: for the time being, Carbon goes only to vetted defenders in cybersecurity. Where does it actually fit in Google's lineup, and what should you do until it becomes available? Oct 29 · 6 min read

One email when something worth reading ships.

Every Tuesday: what changed in Claude Code, Codex and other coding agents, plus new articles. No spam.

From the archive

  1. Oct 28 GPT-6.1 Terra only pays off at half throttle Article
  2. Oct 26 Fewer Subagents, or When Too Many Agents Hurt in Claude... Tutorial
  3. Oct 24 Kimi K3.1 Pro: the best open model is slow and not as cheap as it looks Article
  4. Oct 23 Claude Duet: The Assistant That Reaches Out on Its Own. Once Every Few Hours Claude Code
  5. Oct 22 The First Exploit of the AI Agent Era Agents & security
  6. Oct 20 Add-ons that promise to make Claude Code cheaper: I measured them on 84 runs Claude Code
  7. Oct 13 When Harari Talks About AI After a Booed Macinka Harari
  8. Oct 5 Decision Models: Cheap AI That Picks the Right Answer Tutorial
  9. Oct 2 Mods for Claude Code: Anthropic Lets You Under the Hood Claude Code
  10. Sep 30 OpenAI DevDay 2026: Dots Personal Agents and Other News OpenAI & Codex
  11. Sep 29 The $200 Codex Pro Plan Is Back. With Half the Volume OpenAI & Codex
  12. Sep 21 Who profits when you run an LLM at home Local AI
  13. Sep 19 Jev: the model that doesn't write, it just decides. How to use it and when it pays off Tutorial
  14. Sep 18 Claude Code Projects Now Split Up the Work on Their Own Claude Code
  15. Sep 16 Černá AI Festival Lit Up Ostrava events
  16. Sep 14 How to Tell a Good AI Workshop from a Bad One Workshops
  17. Sep 13 Cursor Projects Shows a Great New Approach to Managing Agents Cursor
  18. Sep 9 Anthropic's head of AI safety testing: We don't have a plan yet for aligning superintelligence Claude Code
  19. Aug 31 OpenClaw 2.0 Does Multiplayer. Watch Out for It! Agents & security
  20. Aug 28 The Case of OpenAI's Rogue AI Agents Attacking Hugging Face OpenAI & Codex
  21. Aug 26 Hardware for Local AI: What to Buy in August 2026, and Whether It Pays Off Local AI
  22. Aug 12 An AI watermark proves touch, not authorship. What should we do about labeling AI content? Claude Code
  23. Aug 11 The Agent Deleted Someone Else's Booking: What AI Agents Do to a Sloppy SaaS Agents & security
  24. Aug 10 Jeff Dean Is Leaving Google. He Has Already Become a Legend. Google
  25. Aug 7 Grok Build Reaches Version 1.0 Grok
  26. Aug 6 Meta Muse Code: When Zuckerberg Teaches AI to Code Meta
  27. Jun 3 Claude Code rewrote /fork. For the second time this month. And this time, it was useful Tutorial
  28. May 31 Dynamic Workflows in Claude Code: An Announced Experiment Now Set to Be Put to the Test Tutorial
  29. May 16 Grok Build CLI – xAI Enters the Terminal Coding Agent Market Grok
  30. May 14 Claude Code Agent view—it’s a whole new way of working Claude Code
  31. May 12 Claude Code also offered /goal for automatically reaching a destination Claude Code
  32. Jun 2, 2025 🐑 Sheep Marketplace — how Tomas Jirikovsky and the Czech Minister of Justice came to Bitcoin Bitcoin
  33. May 14, 2025 Claude Code Hooks — The Complete Guide Tutorial
  34. Mar 7, 2024 When AI comes for those with political power… AI
  35. Oct 13, 2023 The hope of the year: the RISC-V processors RISC-V
  36. Jul 10, 2017 First Czechoslovak radiotelephone networks: AMR Telecom History
  37. May 11, 2016 Strategy of motivation to change the behavior in the wearable and Internet of Things world —… Wearables
  38. Feb 10, 2016 The fairy tale about a single standard for the Internet of Things Internet of Things
  39. Jan 21, 2016 Edge Computing and Fog Computing; or, on the Benefits of Fogging Edge Computing
  40. Jan 4, 2016 WTF of Energy Efficiency: A Quest for the Right Metrics Internet of Things
Patrick Zandl

Patrick Zandl runs Claude Code workshops in Prague and writes about what actually works in AI-assisted software projects, and what doesn’t. This is the English edition of Vibecoding.cz, which covers a broader range of AI tools in Czech.