Four Gemini 4 Argon agents beat Minecraft's Ender Dragon on their own in 27 hours 14 minutes.
AspireAI community · arxiv.org
Four Gemini 4 Argon agents beat Minecraft's Ender Dragon on their own in 27 hours 14 minutes.
Google DeepMind dropped them into a random Easy world with no roles, no human help. Each drove a player through Mineflayer, an open JavaScript library, by writing short programs and reading the output back.
The team wrote 2,783 programs, shared 229 chat messages, died 605 times, and killed the dragon. They split the work themselves, kept notes, recovered each other's items, and worked out how to destroy the ten healing crystals after 21 hours of failure.
A fifth agent, the Observer, watched for cheating and found none. The paper calls this the first end-to-end autonomous Minecraft completion by general coding agents using only the standard library. The whole session cost about $810 at introductory pricing.
It hints at coding agents that can grind through day-long engineering tasks with less human steering.
arXiv:
Read the story and explore more from the AspireAI community.
Two critical PHP remote code execution flaws — one found by GPT-5.6 Sol — were patched on October 21, 2026, and OpenAI published a disclosure framework alongside the fix. Fixed versions: PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35. Both allow unauthenticated remote code execution, and PHP's advisory says risk is highest for mod_php, where a demonstrated exploit triggers before any application code runs. The CVEs are distinct failure modes. CVE-2026-109618 (OOM corruption): out-of-memory handling can interrupt PHP while internal request data is only partially initialized, and request cleanup may then treat the invalid data as valid. CVE-2026-109619 (stale global state): request-owned internal state can survive after its backing memory is freed, and a later request served by the same worker may use that stale state. OpenAI states GPT-5.6 Sol identified the first flaw through its Patch the Planet initiative, and that Wiz independently discovered and reported both vulnerabilities. PHP's maintainers led the fixes and release, with Wiz, Cloudflare and OpenAI contributing research and coordination. Wiz's write-up adds that it used GPT-5.6 Sol and Gemini 4 Argon throughout, with Gemini 4 Argon contributing to finding the vulnerability and validating the patch. OpenAI describes the gap between discovery and public exploitation as a "Defender's Window," proposes a five-stage response framework, and committed $1 billion in subsidised Daybreak model access for organizations with limited security resources. Honest caveats: these are OpenAI's and Wiz's own characterizations, and OpenAI also notes the same capabilities help attackers build offensive tooling faster. PHP 8.1 and older no longer receive updates from the PHP project.