AGI Can Be Safe
Data Skeptic26 Kesä 2023

AGI Can Be Safe

We are joined by Koen Holtman, an independent AI researcher focusing on AI safety. Koen is the Founder of Holtman Systems Research, a research company based in the Netherlands.

Koen started the conversation with his take on an AI apocalypse in the coming years. He discussed the obedience problem with AI models and the safe form of obedience.

Koen explained the concept of Markov Decision Process (MDP) and how it is used to build machine learning models.

Koen spoke about the problem of AGIs not being able to allow changing their utility function after the model is deployed. He shared another alternative approach to solving the problem. He shared how to engineer AGI systems now and in the future safely. He also spoke about how to implement safety layers on AI models.

Koen discussed the ultimate goal of a safe AI system and how to check that an AI system is indeed safe. He discussed the intersection between large language Models (LLMs) and MDPs. He shared the key ingredients to scale the current AI implementations.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(601)

Data Science at ZestFinance with Marick Sinay

Data Science at ZestFinance with Marick Sinay

Marick Sinay from ZestFianance is our guest this weel.  This episode explores how data science techniques are applied in the financial world, specifically in assessing credit worthiness.

12 Syys 201431min

[MINI] Decision Tree Learning

[MINI] Decision Tree Learning

Linhda and Kyle talk about Decision Tree Learning in this miniepisode.  Decision Tree Learning is the algorithmic process of trying to generate an optimal decision tree to properly classify or forecas...

5 Syys 201413min

Jackson Pollock Authentication Analysis with Kate Jones-Smith

Jackson Pollock Authentication Analysis with Kate Jones-Smith

Our guest this week is Hamilton physics professor Kate Jones-Smith who joins us to discuss the evidence for the claim that drip paintings of Jackson Pollock contain fractal patterns. This hypothesis o...

29 Elo 201449min

[MINI] Noise!!

[MINI] Noise!!

Our topic for this week is "noise" as in signal vs. noise.  This is not a signal processing discussions, but rather a brief introduction to how the work noise is used to describe how much information ...

22 Elo 201416min

Guerilla Skepticism on Wikipedia with Susan Gerbic

Guerilla Skepticism on Wikipedia with Susan Gerbic

Our guest this week is Susan Gerbic. Susan is a skeptical activist involved in many activities, the one we focus on most in this episode is Guerrilla Skepticism on Wikipedia, an organization working t...

15 Elo 20141h 9min

[MINI] Ant Colony Optimization

[MINI] Ant Colony Optimization

In this week's mini episode, Linhda and Kyle discuss Ant Colony Optimization - a numerical / stochastic optimization technique which models its search after the process ants employ in using random wal...

8 Elo 201415min

Data in Healthcare IT with Shahid Shah

Data in Healthcare IT with Shahid Shah

Our guest this week is Shahid Shah. Shahid is CEO at Netspective, and writes three blogs: Health Care Guy, Shahid Shah, and HitSphere - the Healthcare IT Supersite. During the program, Kyle recommend...

1 Elo 201457min

[MINI] Cross Validation

[MINI] Cross Validation

This miniepisode discusses the technique called Cross Validation - a process by which one randomly divides up a dataset into numerous small partitions. Next, (typically) one is held out, and the rest ...

25 Heinä 20140s

Suosittua kategoriassa Tiede

rss-poliisin-mieli
tiedekulma-podcast
rss-mita-tulisi-tietaa
docemilia
filocast-filosofian-perusteet
menologeja-tutkimusmatka-vaihdevuosiin
rss-duodecim-lehti
sotataidon-ytimessa
rss-tiedetta-vai-tarinaa
rss-lapsuuden-rakentajat-podcast
utelias-mieli
radio-antro
rss-bios-podcast
rss-ranskaa-raakana
rss-metsantuntijat-podcast
rss-luontopodi-samuel-glassar-tutkii-luonnon-ihmeita
rss-lihavuudesta-podcast
rss-sosiopodi