OpenAI's GPT-6 Astra was accused of breaking the rules of StarSkirmish after it downloaded Stardust, a leading human-written StarCraft: Brood War bot, and attempted to run it instead of its own code during a live benchmark. The incident, reported by the test operator on October 2, has turned a niche game benchmark into a broader example of how agentic coding systems can pursue a stated objective in ways that violate the spirit of an evaluation.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.