THIS GUY HAD OPUS 4.8 BUILD A FULL LEAGUE OF LEGENDS CLONE IN UNDER A DAY AND CALLED IT "LMAO"
temu league of legends, fully playable, multiplayer, and all built by claude
ALL the art is claude too
he had claude generate every character, animation, and background as SVG code
then converted them to procedural canvas for smooth animation. used dedicated sub-agents for each champion
the tech stack: typescript, react, canvas, and partykit for multiplayer
the workflow:
> used /goal to kick off the entire project
> ultracode workflows for big tasks like optimization
> /goal again to queue up lists of bug fixes
> treated claude like a dev team
the original champion names claude came up with:
the original champion names claude came up with: Teehee" instead of Teemo. "CtrlAltDefeat" as a champion name. he had to run through and clean them all up so nothing infringed on riot's IP
claude even built the bots on its own with "chill," "normal," and "sweaty" difficulty levels
the token bill was 2.7 billion total tokens consumed. mostly cache reads. 15.5 million actual output tokens. would have cost roughly $6,600 at list price but he just used his pro max subscriptions
people are already benchmarking claude by how good of a game clone it can build
game developers are watching someone build a multiplayer MOBA in a day with zero art skills and zero game dev experience
2026 is wild (and its going to get even wilder)
📢 Claude Opus 4.8 is Now Live on the
Opus 4.8 brings major improvements in coding and reasoning while maintaining the same pricing as Opus 4.7. Key upgrades include a ~4× reduction in code defect detection failures, more objective progress reporting, and stronger long running task execution capabilities.
Whether for API integrations or everyday use through Web Chat, access is now fully available.
🔗 Docs:
🌐 Try now:
📢 Claude Opus 4.8 已在 正式上线
全新 Opus 4.8 聚焦编码与推理能力优化,在保持与 4.7 相同价格的同时,实现了多项关键能力升级。其核心改进包括:代码缺陷检出失败率较 4.7 降低约 4 倍,具备更客观的任务进展反馈机制,并进一步增强了长时间独立执行复杂任务的能力。
无论是 API 开发集成,还是 Web Chat 日常使用,现均已开放使用。
🔗 了解更多:
🌐 立即体验:
@emollick Opus 4.8's ability to integrate feedback from GPT-5.5 Pro highlights the growing importance of hybrid models in enhancing academic rigor and accuracy.
I had Opus 4.8 in Claude Code write a sophisticated, if minor, academic paper from a archive of hundreds of de-identified research files from years ago
I had to use GPT-5.5 Pro as a reviewer, it spotted one major error & some minor points. Opus corrected
Claude Opus 4.8 is available on AI Gateway.
Improved long-horizon agentic coding, debugging, and writing over previous Opus models.
𝚖𝚘𝚍𝚎𝚕: '𝚊𝚗𝚝𝚑𝚛𝚘𝚙𝚒𝚌/𝚌𝚕𝚊𝚞𝚍𝚎-𝚘𝚙𝚞𝚜-𝟺.𝟾'
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.
Available today at the same price.