Tools Riley Goodside has publicly discussed or demonstrated using. Curated by Magpie's editorial team from podcasts, posts, and public stacks.
About
Riley Goodside is Scale AI's first prompt engineer and the de facto public personality for prompt engineering. He posts adversarial-prompt experiments, jailbreak demonstrations, and rigorous side-by-side model comparisons across X.
ChatGPT is the central subject of Goodside's prompt-engineering experiments. He's been documenting GPT prompt patterns publicly since 2022, including the famous Justin Bieber Super Bowl chain-of-thought example that surfaced reasoning failures and the prompts that fix them. He frames prompt engineering as 'an expressive, mind-bending way to specify tasks to a machine that clarifies your own thinking', and his X feed is one of the most-cited sources for prompt-craft on ChatGPT.
Prompt engineering is an expressive, mind-bending way to specify tasks to a machine that clarifies your own thinking, and *also* a sarcastic pejorative for keyword tricks best left to an optimization algorithm.
Goodside frequently benchmarks Claude against ChatGPT in his prompt experiments and co-authored a Scale AI blog post comparing Anthropic's Claude to OpenAI's ChatGPT in early 2023. He posts side-by-side outputs and behavioural notes that influence how prompt engineers think about model selection on tasks ranging from reasoning to creative writing.
Goodside tests prompt patterns and adversarial inputs against Gemini and reports the behavioural differences on X. He treats Gemini as one of the canonical frontier models worth probing, with particular attention to where Google's safety tuning produces different failure modes than OpenAI or Anthropic.
These tools have been mentioned by the people featured in podcasts, interviews, posts, and other public media. Source links and citations are included wherever possible. Magpie AI has no direct relationship with the people on these pages. Spot a missing tool or a wrong attribution? Suggest a correction →