Matt Shumer runs 24/7 Opus 5 game loop

// 3h agoPRODUCT LAUNCH

Matt Shumer runs 24/7 Opus 5 game loop

Matt Shumer announced an effort to build a new game by running a continuous Opus 5 agentic loop 24/7 on 20x Max subscriptions. He shared an email sign-up link for early access and noted that while non-stop agentic execution is costly, token consumption remains manageable, with the core prompts made publicly available.

// ANALYSIS

Running continuous 24/7 autonomous agent loops on frontier models showcases the evolving frontier of automated game development and vibe coding.

–Demonstrates an ambitious implementation of perpetual agentic execution using high-tier Claude models.
–Highlights growing interest in fully hands-off AI software construction despite subscription and token costs.
–Engages community discussion around prompt sharing, token economics, and scalable AI workflows.

// TAGS

matt-shumeropus-5autonomous-agentsgame-developmentai-coding

DISCOVERED

3h ago

2026-07-27

PUBLISHED

6h ago

2026-07-26

RELEVANCE

7/ 10

AUTHOR

mattshumer_

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE26m ago

OpenCode 1.18.6 fixes MCP refresh and branch caches

OpenCode version 1.18.6 introduces key stability fixes and performance improvements across its desktop application and underlying client interfaces. This update resolves provider and Model Context Protocol (MCP) refresh issues in App v1, stabilizes v2 client compatibility by pinning the UI to a versioned `@opencode-ai/client` snapshot, and isolates remote reference caches by git branch to prevent cross-branch state collisions.

OPEN SOURCE1h ago

ESP32 AI Runs 28.9M Model at 9.5 Tokens/Sec

ESP32 AI is an architectural experiment by slvDev that runs a 28.9-million-parameter TinyStories language model locally on an $8 ESP32-S3 microchip without relying on external cloud servers. By keeping a 25-million-parameter embedding table in memory-mapped SPI flash to fetch token rows on demand, the project successfully circumvents tight microcontroller RAM limitations while maintaining a generation throughput of approximately 9.5 tokens per second.

OPEN SOURCE1h ago

Open Science v0.7.2 boosts research workflow transparency

AIPOCH has released Open Science v0.7.2, an update to its open-source, model-agnostic AI workbench for scientific discovery. The new release prioritizes making AI research workflows more transparent, controllable, and easier to manage as researchers increasingly rely on autonomous agents for complex scientific tasks.