This Day in AI Podcast

EP35: AI Safety Gone Mad, Stable 3B Cheese Test, GPT4 Vision & DALL-E 3 Diversity + Sydney is BACK!

14 snips
Oct 6, 2023
In this podcast, they discuss the wild world of AI image generation and vision, including racist cartoon captions, heartfelt poetry by Bing, and teaching AI to forget unwanted knowledge. They debate AI safety controls, the limitations of Turnitin for detecting AI-generated writing, biases in AI-generated images, and the potential disappearance of captchas. They also explore censorship potential in AI models and express gratitude for audience engagement.
Ask episode
AI Snips
Chapters
Transcript
Episode notes
ADVICE

Rework Exams For An AI-Enabled Classroom

  • Educators should assume AI usage and redesign assessments (e.g., in-person oral exams) to test understanding.
  • Adopt evaluation methods that minimize AI-written false positives and emphasize live demonstration of knowledge.
ANECDOTE

Cheese Test: Tiny Model Passes Roleplay

  • The hosts ran the 'cheese test' on Stable LM 3B and Mistral to compare reasoning quirks.
  • Stable 3B correctly followed the cheese-themed doctor persona and produced the expected diagnosis and lament.
INSIGHT

Image Models Alter Prompts For 'Safety' Reasons

  • DALL·E 3 and Bing Vision appear to inject diversity and safety instructions, altering user prompts and outputs.
  • Prompt injection for 'diversity' can produce unrelated or biased images instead of honoring the user's request.
Get the Snipd Podcast app to discover more snips from this episode
Get the app