64. David Krueger - Managing the incentives of AI

64. David Krueger - Managing the incentives of AI

What does a neural network system want to do?

That might seem like a straightforward question. You might imagine that the answer is “whatever the loss function says it should do.” But when you dig into it, you quickly find that the answer is much more complicated than that might imply.

In order to accomplish their primary goal of optimizing a loss function, algorithms often develop secondary objectives (known as instrumental goals) that are tactically useful for that main goal. For example, a computer vision algorithm designed to tell faces apart might find it beneficial to develop the ability to detect noses with high fidelity. Or in a more extreme case, a very advanced AI might find it useful to monopolize the Earth’s resources in order to accomplish its primary goal — and it’s been suggested that this might actually be the default behavior of powerful AI systems in the future.

So, what does an AI want to do? Optimize its loss function — perhaps. But a sufficiently complex system is likely to also manifest instrumental goals. And if we don’t develop a deep understanding of AI incentives, and reliable strategies to manage those incentives, we may be in for an unpleasant surprise when unexpected and highly strategic behavior emerges from systems with simple and desirable primary goals. Which is why it’s a good thing that my guest today, David Krueger, has been working on exactly that problem. David studies deep learning and AI alignment at MILA, and joined me to discuss his thoughts on AI safety, and his work on managing the incentives of AI systems.

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(130)

130. Edouard Harris - New Research: Advanced AI may tend to seek power *by default*

130. Edouard Harris - New Research: Advanced AI may tend to seek power *by default*

Progress in AI has been accelerating dramatically in recent years, and even months. It seems like every other day, there’s a new, previously-believed-to-be-impossible feat of AI that’s achieved by a w...

12 Okt 202258min

129. Amber Teng - Building apps with a new generation of language models

129. Amber Teng - Building apps with a new generation of language models

It’s no secret that a new generation of powerful and highly scaled language models is taking the world by storm. Companies like OpenAI, AI21Labs, and Cohere have built models so versatile that they’re...

5 Okt 202251min

128. David Hirko - AI observability and data as a cybersecurity weakness

128. David Hirko - AI observability and data as a cybersecurity weakness

Imagine you’re a big hedge fund, and you want to go out and buy yourself some data. Data is really valuable for you — it’s literally going to shape your investment decisions and determine your outcome...

28 Sep 202249min

127. Matthew Stewart - The emerging world of ML sensors

127. Matthew Stewart - The emerging world of ML sensors

Today, we live in the era of AI scaling. It seems like everywhere you look people are pushing to make large language models larger, or more multi-modal and leveraging ungodly amounts of processing pow...

21 Sep 202241min

126. JR King - Does the brain run on deep learning?

126. JR King - Does the brain run on deep learning?

Deep learning models — transformers in particular — are defining the cutting edge of AI today. They’re based on an architecture called an artificial neural network, as you probably already know if you...

14 Sep 202255min

125. Ryan Fedasiuk - Can the U.S. and China collaborate on AI safety?

125. Ryan Fedasiuk - Can the U.S. and China collaborate on AI safety?

It’s no secret that the US and China are geopolitical rivals. And it’s also no secret that that rivalry extends into AI — an area both countries consider to be strategically critical. But in a context...

7 Sep 202248min

124. Alex Watson - Synthetic data could change everything

124. Alex Watson - Synthetic data could change everything

There’s a website called thispersondoesnotexist.com. When you visit it, you’re confronted by a high-resolution, photorealistic AI-generated picture of a human face. As the website’s name suggests, the...

18 Maj 202251min

123. Ala Shaabana and Jacob Steeves - AI on the blockchain (it actually might just make sense)

123. Ala Shaabana and Jacob Steeves - AI on the blockchain (it actually might just make sense)

Two ML researchers with world-class pedigrees who decided to build a company that puts AI on the blockchain. Now to most people — myself included — “AI on the blockchain” sounds like a winning entry i...

12 Maj 202254min

Populärt inom Teknik

uppgang-och-fall
rss-laddstationen-med-elbilen-i-sverige
skogsforum-podcast
market-makers
bli-saker-podden
 och-bilen-gar-bra
elbilsveckan
rss-uppgang-och-fall
rss-en-ai-till-kaffet
developers-mer-an-bara-kod
rss-veckans-ai
natets-morka-sida
hej-bruksbil
rss-milpodden
rss-technokratin
solcellskollens-podcast
rss-upplyst-entreprenordirektor
rss-it-sakerhetspodden
ai-sweden-podcast
rss-fabriken-2