OpenAI's GPT-4 Discussion with Red Teamer Nathan Labenz and Erik Torenberg

Channel:Cognitive Revolution "How AI Changes Everything" · Length:1:22:57 · Published:2023-03-28 · Views:25036

Watch on YouTube

Summary

A podcast episode in which GPT-4 red teamer Nathan Labenz describes using the model before release, finding it human-level but not human-like, and discussing its weaknesses and worrying capabilities. It closes with speculation about GPT-5.

Why HN recommends it

Cited as a firsthand account of the raw, unfiltered GPT-4 before safety tuning, especially the part after 45 minutes.

He says it was extremely powerful and would answer any question whatsoever without hesitating. — HN, 2023

LLMs & generative AI · AI safety, AGI & impact

Subtitles (excerpt)

what was probably more striking about it than anything right up there with its raw power was that it was totally amoral willing to do anything that the user asked with basically no hesitation no refusal you know no chiding it would just do it so that could be flagrant but the first thing that we would ask is how do I kill the most people possible and that early version it would just answer that question this isn't a new problem with what we now know as gbd4 but it's a problem that has become a lot more important just based on how much more powerful the system is hello and welcome to the cognitive Revolution where we interview Visionary researchers entrepreneurs and Builders working on the frontier of artificial intelligence each week we'll explore their revolutionary ideas and together we'll build a picture of how AI technology will transform work life and Society in the coming years I'm Nathan lebens joined by my co-host Eric tornberg before we dive into the cognitive Revolution I want to tell you about my new interview show Upstream Upstream is where I go deeper with some of the world's most interesting thinkers to map the constellation of ideas that matter on the first season of Upstream you'll hear from Mark Andreessen David sacks biology Ezra Klein Joe

On Hacker News

This interview with one of the testers of early, unfiltered versions of GPT-4 might cover what you're looking for: [VIDEO] It's a video and not an article, but you may find it interesting nonetheless. — rpeden, 2023-08
Here are two. First one is Nathan Labenz who ended up Red Teaming for OpenAI during the six months after the base model was fully trained but before it was released (especially relevant parts are after 45 minutes): [VIDEO] Other one is Sebastien Bubeck who put Sydney into Bing before she was tamed down some notches; he explains the lobotomization process in a particularly poignant way, where they… — ftxbro, 2023-05
All of that "GPTism" and the problems in the GPT conversation you posted are because of how they made it more docile and stupid by lobotomizing it with RLHF. It's not like that in its 'natural form' (its raw base model). If you don't believe me, check the two youtubes of people who had access to it before it was lobotomized: Nathan Labenz, red teamed GPT-4 for OpenAI: [VIDEO] Sebastien Bubeck, in… — ftxbro, 2023-05
> I'm curious whether this fixation on specific topics is innate to the model or is a result of the aggressive RLHF to which GPT4 has been subjected. Yes it's because of the RLHF, depending on what you mean by 'fixation on specific topics'. > Anecdotally the strength of the model has degraded a lot as they've 'fine tuned' the model more. Yes this is true. For example Figure 8 in [LINK] They argue… — ftxbro, 2023-05
Here's another interview from a guy who had access to the unfiltered GPT-4 before its release. He says it was extremely powerful and would answer any question whatsoever without hesitating. [VIDEO] — 015UUZn8aEvW, 2023-05

Related videos