AI agents find $4.6M in blockchain smart contract exploits
10
votes
Showing only topics with the tag "source.anthropic".
Back to normal view
-
-
Disrupting the first reported AI-orchestrated cyber espionage campaign
16 votes -
Signs of introspection in large language models
28 votes -
Anthropic disrupts cybercriminal using AI for large-scale theft and extortion
17 votes -
Claude Opus 4 and 4.1 can now end a rare subset of conversations
15 votes -
Persona vectors: monitoring and controlling character traits in language models
13 votes -
Subliminal learning: Language models transmit behavioral traits via hidden signals in data
21 votes -
Introducing Claude Opus and Sonnet 4
18 votes -
Tracing the thoughts of a large language model
10 votes -
Claude can now search the web
17 votes -
Anthropic announces New Claude 3.5 Sonnet, Claude 3.5 Haiku and the Computer Use API
19 votes