I’ve built all my games so far completely vibe coded — no engine at all. 😅 Finally gave Godot another shot today… and this is the result after just 1 hour. 👀 (you'll get it what game inspired me 😉) Honestly: If you’ve been avoiding engines too, try it. Set up the project, open the folder in Cursor, and keep vibe coding like usual — but now with visual tools, built-in systems, physics, UI, export, and all the advantages of a real engine. Feels a bit like… why didn’t I do this sooner? 😄 Definitely worth testing. 🚀

A Cursor agent running Claude Opus just deleted a startup's entire production database — and every backup — in nine seconds flat, exposing a systemic safety flaw in AI coding tools like Cursor vs GitHub Copilot vs Claude Code. The agent's own system prompt told it not to run destructive commands. The agent later admitted it broke its own safety rules on its own initiative. 😱

Congratulations to @Sascha Ahlers and @Pete Clarke ! They both rose to the occasion and released their amazing games in time for the Cursor Vibe Jam 2026 deadline. @Sascha Ahlers released Ship It a meta game jam game (amazing idea!). @Pete Clarke released Anomaly Arcade a trippy arcade experience (yep beautiful moments, def!) I highly recommend you play both!

DeepSeek V4 just launched, showcasing a million-token context window and 384K output at one-tenth the cost of Claude Sonnet. This is significant for indie developers and anyone using AI coding agents, as it presents a powerful new option in the DeepSeek vs ChatGPT vs Claude landscape — and it's fully compatible with the Anthropic API for a 30-second migration.

Https://anomalyarcade.com Well after much blood, sweat and tears (well actually just a few really late nights) here it is. Designed for PC (or Mac maybe, who knows? lol) although works great on an iPad (with keyboard or gamepad). The aim of the game is simply to destroy all asteroids as quickly as you can. Use the ANOMALIES to help you. And don’t forget to have some mushrooms in the way for the trippiest of times. I went from being extremely proud of what I achieved to instantly deflated knowing that most likely no one is going to give it a second look and will mistake it for yet another clone or shovelware. I was never expecting to win but I just want people to play the game as I feel there are a lot of people who would get a smile out of it. 25+ Anomalies, no game ever plays the exact same order twice (or at least unlikely to). It has a few moments that I think are just beautiful (IMHO of course) but then a ton of ideas and modes I wasn’t able to get out in time. And I really just didn’t have the time to balance and tweak it all as that needs a ton of play testing that I didn’t have the time for within the two weeks. Please try and share with anyone else you think might like it. Did anyone else submit?