EP35: AI Safety Gone Mad, Stable 3B Cheese Test, GPT4 Vision & DALL-E 3 Diversity + Sydney is BACK!
whatshot 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.
01:17:39
forum Ask episode
web_stories AI Snips
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
volunteer_activism 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.
question_answer 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.
insights 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
Thanks for helping us reach 2K subs here on YouTube!
This week we dive into the wild world of AI image generation and vision, from racist cartoon captions to heartfelt poetry written by Bing. We discuss the implications of teaching AI to forget unwanted knowledge, and debate whether safety controls are protecting users or limiting creativity. Get ready for philosophical ponderings, hilarious experiments, and our signature irreverent takes as we explore the latest AI advances and absurdities. Whether you're an expert or just fascinated by the future, this episode will challenge your thinking and give you plenty to discuss with friends.
CHAPTERS ====== 00:00 - Fooling Bing Vision to Solve Captcha 00:26 - Meta's Messenger AI Stickers Out of Control! AI Safety Discussion 06:17 - More Safety Nonsense: The Low-Resource Language Jailbreak GPT-4 Paper 9:36 - More on Mistral 7B (Safety and Positive Reception) 17:31 - Friends and Foes of Open Source AI & Is Anthropic a Crypto-like Scam for Billions? 21:26 - Turnitin Thinks It Can Detect AI, Being a Student in an AI World 24:25 - Stable 3B LLM Review and Cheese Test Results 38:48 - DALL-E 3 Road Test on ChatGPT & Diversity Prompt Injection Problems 48:12 - Using Bing GPT4-Vision to Solve Captchas for Grandma 51:01 - The Dawn of LLMs, Explorations with GPT-4Vision Paper + Possibilities of AI Vision 1:04:00 - Who's Harry Potter? Making LLMs forget 1:09:00 - Google Assistant with Bard AI 1:10:18 - LLaMA Long 32K Initial Thoughts 1:12:40 - Sydney Bing is Back BABY! 1:15:36 - Comments on Discord Rollout and Survey Response