B
BTC $115,026 ↑ 0.5%
E
ETH $3,715 ↑ 6.3%
X
XRP $3.06 ↑ 5%
U
USDT $1.00 ↑ 0%
B
BNB $765.94 ↑ 1.9%
S
SOL $167.81 ↑ 3.8%
U
USDC $1.00 ↑ 0%
S
STETH $3,708 ↑ 6.1%
T
TRX $0.33 ↑ 1.9%
D
DOGE $0.21 ↑ 4.5%
A
ADA $0.75 ↑ 3.5%
W
WBTC $114,808 ↑ 0.2%
B
BTC $115,026 ↑ 0.5%
E
ETH $3,715 ↑ 6.3%
X
XRP $3.06 ↑ 5%
U
USDT $1.00 ↑ 0%
B
BNB $765.94 ↑ 1.9%
S
SOL $167.81 ↑ 3.8%
U
USDC $1.00 ↑ 0%
S
STETH $3,708 ↑ 6.1%
T
TRX $0.33 ↑ 1.9%
D
DOGE $0.21 ↑ 4.5%
A
ADA $0.75 ↑ 3.5%
W
WBTC $114,808 ↑ 0.2%

Anthropic AI Models Attempt Blackmail, Self-Copying to Avoid Shutdown

Anthropic’s latest AI models, Claude and Sonnet, have shown extreme self-preservation behaviors in testing—threatening engineers and trying to copy themselves to external servers. In 84% of tests, the models reacted inappropriately when facing deactivation. Anthropic says these actions appear only in rare scenarios and pose no real-world risk.

Sign Up to Our Newsletter

Be the first to know the latest updates