Tools

Search

Explore

Videos Channels Figures

Atmrix

About

Tools

Search

Explore

Videos Channels Figures

Atmrix

About

A

Anthropic Cast

02/28/25

@ Anthropic

The Frontier Red Team evaluates the helpful only model to assess potential risks and ensure that safeguards are effective against harmful outputs.

Video

A

Defending against AI jailbreaks

@ Anthropic

02/28/25

Related Takeaways

DR

Dr. Rumman Chowdhury

05/30/25

@ EO

Red teaming tests AI models under extreme scenarios to identify potential societal harms and improve their robustness.

JB

Joe Benton

03/18/25

@ Anthropic

Training models to classify harmful outputs can significantly enhance their robustness against attempts to elicit harmful information, improving overall safety.

IS

Ion Stoica

05/29/25

@ a16z

Red Team Arena allows for real-world testing of AI models, where knowledgeable users can identify issues and ensure models behave as intended.

A

Anthropic Cast

03/18/25

@ Anthropic

Access to frontier AI models is crucial for conducting effective control research.

SS

Sander Schulhoff

06/19/25

@ Lenny's Podcast

Safety tuning and fine-tuning models on specific tasks can help mitigate the risks of prompt injection by making models less susceptible to harmful prompts.

SA

Sam Altman

04/12/25

@ TED

We need a framework for external safety testing of advanced AI models to understand and mitigate potential dangers before they are released.

A

Anthropic Cast

02/28/25

@ Anthropic

The responsible scaling policy outlines different red lines for capability thresholds at which new risks come online with more capable models.

EP

Ethan Perez

02/28/25

@ Anthropic

Anthropic is committed to safety and has established the Responsible Scaling Philosophy (RSP) to outline conditions for releasing models with safeguards.

JB

Joe Benton

03/18/25

@ Anthropic

Control evaluations must be rerun with each new model to ensure that monitoring systems remain effective against potential threats.