1min snip

Soft Skills Engineering cover image

Episode 405: Scaled agile pain and top-heavy team

Soft Skills Engineering

NOTE

Innovative ways to manipulate LLM prompts

By manipulating the prompt response of a large language model (LLM), researchers were able to generate a fake sensitive data by encoding it in base 64. Additionally, another example highlights how a person tricked an LLM into providing a medical diagnosis by pretending to be creating a quiz for a medical school. These instances showcase innovative ways to exploit LLM prompts for desired outcomes.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode