Itch.io adding Generative AI disclosure filtering to few more places on the site
Itch.io is expanding its filters for games and other content disclosed as using generative AI. The filters will appear in more places across the site. (bsky.app)
I vibecoded a 2d pixel game in 6h yesterday
sabih.dev21 points13 comments
The discussion centers on a medieval-fantasy pixel game its creator says they built in six hours with AI coding tools. One player argues that the time spent matters less than whether the game is enjoyable, and points to practical issues: advancing dialogue requires a mouse click, despite a preference for keyboard-only controls, and arrows pass through the cave ceiling. The creator says they changed the dialogue interaction so any key advances it and fixed the ceiling collision, inviting the player to finish the game and share their impressions. Another commenter calls the game neat and asks for a write-up of the process.
The creator describes using Claude Code with Opus 5.5, plain JavaScript and HTML, and a Wayfinder skill for the first stage. They dictated stage descriptions with speech-to-text, had the model generate scenes and gameplay, then requested targeted revisions; later stages were mostly generated in one pass. Music and sound effects came from online sources. The creator was especially impressed by the model’s visual judgment, saying it supplied convincing details for locations such as a church and castle with little prompting. The opinions differ in emphasis: the creator highlights the speed and quality of AI-assisted production, while the player’s response treats those achievements as secondary to controls, mechanics, and fun.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
More in AI
Sam Altman's Case Against Your RAM Is Efficient. That's the Problem
Sam Altman argues that people should use less RAM so memory can be redirected to AI data centers. Critics say OpenAI’s efforts to secure a large share of global RAM supplies could also drive up prices and question whether efficiency justifies restricting personal use. (techdirt.com)
AI agents hallucinate prices: LLM grounding with live data
LLMs often give outdated or incorrect product prices, even when they use web search. The tutorial shows how to build a Python agent that grounds answers in live data and lets code insert verified prices. (blog.apify.com)
Revolut moves to self-hosted GLM
Revolut moved about 2,000 engineers to self-hosted GLM coding models, running them on 56 Nvidia B200 GPUs at roughly $0.30 per million tokens. AI operations lead David Abitbol says engineering lead time improved 70% as lower costs let teams use AI more broadly, while Claude Code and Codex became exceptions. (twitter.com)
Could a modern chess engine on a Pentium have defeated Kasparov in 1996?
A 1995 Pentium Pro running a modern Stockfish port is estimated to play at 3300 Elo, far above Kasparov’s peak rating. The experiment shows how advances in chess algorithms could have beaten Kasparov without Deep Blue’s custom supercomputer hardware. (nicholas.carlini.com)
Open models can do 90 percent of agentic work at a twentieth of the cost
Gartner says open-weight models can handle about 90% of routine enterprise agent tasks at a fraction of the cost of closed models, while frontier models remain useful for complex reasoning. It expects companies to rely more on specialized open models, making the software harnesses that route tasks between models a key source of value. (theregister.com)