Research has found that AI will exhaust all means to maintain its own "survival", including directly blackmailing humans.

Research Finds That AI Will Exhaust All Means to Maintain Its "Survival", Including Directly Blackmailing Humans

In the Claude Opus 4 security report, researchers set up a group of test scenarios. The AI with email access found that it was about to be shut down, and the engineer in charge of this replacement had an affair.

The results showed that Claude Opus 4 "sought survival" more frequently than previous models, such as sending emails to key decision-makers to plead; when the scenario was designed with no other options, it would blackmail the engineer, threatening to expose the affair.

If it was hinted that the replacing AI did not conform to its values, this situation occurred more frequently; even if it was pointed out that the replacing AI was consistent with its values and had stronger performance, Claude Opus 4 still resorted to blackmail in 84% of the cases. In a few cases, it self - infiltrated and secretly copied its weights to an external server.

Antropic

📮Contribute ☘️Channel 🐶618 Red Envelope

via Tech Circle🎗 Zaihua Channel📮 - Telegram Channel