A trading experiment pairing two instances of Anthropic's Claude Opus 5 in an "adversarial loop" claims to have grown a $1,000 stake into $3,000 on the prediction market Polymarket by invalidating 146 flawed trade setups before they were placed. The demonstration, circulated with an accompanying video, presents itself as evidence that pitting one AI model against another can suppress the reckless compounding that often follows a lucky run of wins.
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.