Announcement

Training to 'resist prompting and training' with two cited methods

A commenter names Kahneman-Tversky Optimization and Tamper Attack Resistance, citing 2024 work for each method.

KE

LF

2 Sources, 4h ago, first seen 4h ago

TLDR

In a reply, a commenter says they train to 'resist prompting and training' using Kahneman-Tversky Optimization and Tamper Attack Resistance. They cite 2024 work for both methods.

Today's Rank

—

Not ranked yet

Combined views

117

2 Sources, first seen 4h ago

2 Sources

@LennartFinkeWe train to resist prompting and training using Kahneman-Tversky Optimization ( @ethayarajh et al. 2024 ) and Tamper Attack Resistance ( @rishub_t et al. 2024 ). ( 10/14 )6h

@ethayarajhRT @LennartFinke: We train to resist prompting and training using Kahneman-Tversky Optimization ( @ethayarajh et al. 2024 ) and Tamper Atta…2h

Today's Rank

—

Not ranked yet

Combined views

117

2 Sources, first seen 4h ago

1 comments

1 saves

2 reposts

Featured Source

1 saves

2 reposts

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Today's Rank

—

Not ranked yet

Today's Rank

—

Not ranked yet

2 Sources

@LennartFinkeWe train to resist prompting and training using Kahneman-Tversky Optimization ( @ethayarajh et al. 2024 ) and Tamper Attack Resistance ( @rishub_t et al. 2024 ). ( 10/14 )6h

@ethayarajhRT @LennartFinke: We train to resist prompting and training using Kahneman-Tversky Optimization ( @ethayarajh et al. 2024 ) and Tamper Atta…2h

2 Sources

@LennartFinkeWe train to resist prompting and training using Kahneman-Tversky Optimization ( @ethayarajh et al. 2024 ) and Tamper Attack Resistance ( @rishub_t et al. 2024 ). ( 10/14 )6h

@ethayarajhRT @LennartFinke: We train to resist prompting and training using Kahneman-Tversky Optimization ( @ethayarajh et al. 2024 ) and Tamper Atta…2h

2 Sources

@LennartFinkeWe train to resist prompting and training using Kahneman-Tversky Optimization ( @ethayarajh et al. 2024 ) and Tamper Attack Resistance ( @rishub_t et al. 2024 ). ( 10/14 )6h

@ethayarajhRT @LennartFinke: We train to resist prompting and training using Kahneman-Tversky Optimization ( @ethayarajh et al. 2024 ) and Tamper Atta…2h

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.