Dive into the thrilling world of Prompt Wars, where players craft prompts to outsmart AI in an intense battle of wits. Explore the fascinating advancements in AI cognition and digital neuroscience, revealing how machines learn and create. Discover Mason's low-effort podcast knowledge base experiment and the dark side of AI, including the risks posed by deepfakes and deceptive video chatbots. This discussion highlights not just the innovations but the ethical challenges and potential dangers of AI in our lives.
57:19
forum Ask episode
web_stories AI Snips
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
question_answer ANECDOTE
Prompt Wars
Mason introduces Prompt Wars, an LLM-based game inspired by Core Wars.
Players craft prompts ("spells") to compete against others, aiming to have their prompt echoed back by the LLM.
insights INSIGHT
Visibility Paradox
Prompt Wars presents a "visibility paradox": successful prompts reveal themselves to others.
The better a prompt performs, the more it's exposed, creating a trade-off between effectiveness and secrecy.
question_answer ANECDOTE
Pirate Spell Experiment
Mason experimented with a "pirate stuff" spell in Prompt Wars.
It included pirate phrases, scoring points for each use, but the opponent's prompt still dominated.
Get the Snipd Podcast app to discover more snips from this episode
We explore "Prompt Wars," an asynchronous multiplayer LLM competition where players craft prompts to battle against others in a fascinating game of AI manipulation
We dive into Anthropic's latest research on AI cognition and circuit tracing - essentially digital neuroscience for large language models
Mason shares his AI BodgeLab experiment creating a low-effort podcast knowledgebase
We discuss the potential risks of AI video chatbots as agents of surroundings and mayhem.
===== Learn more about the upcoming OFFENSIVE CYBER DECEPTION MASTERCLASS (Las Vegas, August 2-5, 2025) please visit this link: https://tinyurl.com/5ytpvjv7 =====