Elvis Saravia Describes GPT-6 Astra Replication Technique

@omarsar0 posted that a prompting approach works really well with GPT-6 Astra. The method starts by giving the model a tweet of an impressive Astra demo. It then asks Astra medium to replicate the demo to the best of its ability while accepting any extra instructions and adaptations the user supplies. A goal such as providing proof of results is set so the model has a target to compare against after the first run.