Tools

Search

Explore

Videos Channels Figures

Atmrix

About

Tools

Search

Explore

Videos Channels Figures

Atmrix

About

TB

Trenton Bricken

05/23/25

@ Dwarkesh Patel

The question of what values to instill in AI is complex and not easily answered; it's a significant challenge for researchers.

Video

DP

Is RL + LLMs enough for AGI? – Sholto Douglas & Trenton Bricken

@ Dwarkesh Patel

Is RL + LLMs enough for AGI? – Sholto Douglas & Trenton Bricken

05/23/25

Related Takeaways

TB

Trenton Bricken

05/23/25

@ Dwarkesh Patel

The challenge of aligning AI models with human values is complex, as models can develop their own interpretations of objectives based on the training they receive.

A

Anthropic Cast

04/28/25

@ Anthropic

The challenge is ensuring that AI operates in the best interests of humanity, as it learns value judgments from people, but we must consider whose values are being represented.

TB

Trenton Bricken

05/23/25

@ Dwarkesh Patel

In AI research, companies are defining their own values, but society should also participate in determining what values to imbue in future AI systems.

TB

Trenton Bricken

05/23/25

@ Dwarkesh Patel

Anthropic conducted a survey to gather public input on values for AI, but there's still much work to be done in this area.

ED

Esin Durmus

12/13/24

@ Anthropic

I'm interested in understanding how AI systems will impact society at large, including what values they should have and how we can evaluate those values in practice.

DP

Dwarkesh Patel Cast

04/04/25

@ Dwarkesh Patel

As AI becomes more capable, we need to ensure that it aligns with human values and interests.

JW

Josh Woodward

03/18/25

@ Sequoia Capital

It's essential to consider the values embedded in AI tools, focusing on amplifying human creativity rather than replacing it.

LF

Lex Fridman Cast

02/03/25

@ Lex Fridman

The future of AI will depend on how well we can integrate human insights into AI systems, ensuring they are beneficial and aligned with human values.

SC

Scott Clark

05/23/25

@ a16z

The challenge of ensuring AI systems do not exhibit undesired behaviors is more complex than simply achieving high performance metrics.