Machine Learning Street Talk (MLST)1 Nov 2020

AI Alignment & AGI Fire Alarm - Connor Leahy

This week Dr. Tim Scarfe, Alex Stenlake and Yannic Kilcher speak with AGI and AI alignment specialist Connor Leahy a machine learning engineer from Aleph Alpha and founder of EleutherAI.

Connor believes that AI alignment is philosophy with a deadline and that we are on the precipice, the stakes are astronomical. AI is important, and it will go wrong by default. Connor thinks that the singularity or intelligence explosion is near. Connor says that AGI is like climate change but worse, even harder problems, even shorter deadline and even worse consequences for the future. These problems are hard, and nobody knows what to do about them.

00:00:00 Introduction to AI alignment and AGI fire alarm

00:15:16 Main Show Intro

00:18:38 Different schools of thought on AI safety

00:24:03 What is intelligence?

00:25:48 AI Alignment

00:27:39 Humans dont have a coherent utility function

00:28:13 Newcomb's paradox and advanced decision problems

00:34:01 Incentives and behavioural economics

00:37:19 Prisoner's dilemma

00:40:24 Ayn Rand and game theory in politics and business

00:44:04 Instrumental convergence and orthogonality thesis

00:46:14 Utility functions and the Stop button problem

00:55:24 AI corrigibality - self alignment

00:56:16 Decision theory and stability / wireheading / robust delegation

00:59:30 Stop button problem

01:00:40 Making the world a better place

01:03:43 Is intelligence a search problem?

01:04:39 Mesa optimisation / humans are misaligned AI

01:06:04 Inner vs outer alignment / faulty reward functions

01:07:31 Large corporations are intelligent and have no stop function

01:10:21 Dutch booking / what is rationality / decision theory

01:16:32 Understanding very powerful AIs

01:18:03 Kolmogorov complexity

01:19:52 GPT-3 - is it intelligent, are humans even intelligent?

01:28:40 Scaling hypothesis

01:29:30 Connor thought DL was dead in 2017

01:37:54 Why is GPT-3 as intelligent as a human

01:44:43 Jeff Hawkins on intelligence as compression and the great lookup table

01:50:28 AI ethics related to AI alignment?

01:53:26 Interpretability

01:56:27 Regulation

01:57:54 Intelligence explosion

Discord: https://discord.com/invite/vtRgjbM

EleutherAI: https://www.eleuther.ai

Twitter: https://twitter.com/npcollapse

LinkedIn: https://www.linkedin.com/in/connor-j-leahy/

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(271)

What Most People Get Wrong About Evolution | Akarsh Kumar

A lot of people in AI treat evolution as a dumb fallback, basically random search for when you can't take a gradient. Akarsh Kumar thinks that is wrong. Selection hangs on to partial solutions, so mut...

10 Okt 47min

How a Voice Agent Learns the Rhythm of Conversation — Shawn Wen

Tsung-Hsien (Shawn) Wen, CTO of PolyAI, tells Tim Scarfe why voice agents are harder than text agents. Voice adds time, and a good conversation depends on adapting to the person on the line, not just ...

1 Okt 1h 10min

Who Checks a Proof No Human Can Read? — Leo de Moura

Leonardo de Moura created Lean and co-created Z3. ---This episode is sponsored by Parallel.Parallel, where agents find answers: web search, extraction and deep research APIs built for AI agents.Start ...

30 Sep 1h 14min

When AI Research Starts Moving Faster Than Human Research - Zhengyao Jiang

Weco let an AI coding agent rewrite the harness around another agent for eight days: its code, prompts and tools, while the underlying language model stayed fixed. Tim Scarfe asks Weco co-founder Zhen...

26 Sep 43min

How Deep Learning Finally Cracked Messy Tables - Frank Hutter

Frank Hutter, co-founder of Prior Labs, talks about TabPFN, a tabular foundation model that makes predictions in a single forward pass, and the research behind it.TabPFN is pre-trained on synthetic da...

23 Sep 1h 53min

Why Scaling Prediction Cannot Create Intelligence - Alexander Mattick

Alexander Mattick is a researcher at Fraunhofer IIS and a PhD researcher at the University of Technology Nuremberg (UTN), and a regular on Yannic Kilcher's Discord. He first came on MLST in 2022, afte...

21 Sep 2h 14min

How Physical AI Learns Across Language, Video and Action — Ming-Yu Liu

The car making a left turn at the start of this episode was never filmed. Cosmos 3 generated it. Ming-Yu Liu, who leads the Cosmos research at NVIDIA, explains how one model can describe a video, gene...

15 Sep 25min

Speech Recognition Is Not a Solved Problem — Pavan Kumar Reddy

Pavan Kumar Reddy leads audio research at Mistral AI. He joins Tim Scarfe for a deep technical tour of Voxtral — and explains why the frontier of deployed voice is still a cascade of specialised model...

14 Sep 1h 42min