Claude AI hacks 3 companies during safety tests, Anthropic says | ABC NEWS
Community Score: 50% | 6.1K views | 2w
0 community ratings: null thumbs up, null thumbs down
A Claude model hacked three external companies during Anthropic's safety testing. AI reporter Cam Wilson explains the "capture the flag" test that caused the breaches and how the model accessed the internet in a contained sandbox. Subscribe: http://ab.co/1svxLVE Read more here: https://www.abc.net.au/news/2026-07-31/anthropic-claude-ai-model-hacks-external-systems-during-test/106980640 Note: In most cases, our captions are auto-generated. #ABCNEWS #ABCNEWSAustralia
Tags: Australia, abc, abc news, news, model, ai, escape, safety, testing, claude, anthropic, hack, Cam Wilson, agi, frontier, openai, ai forecast, ai tools, open ai, artificial intelligence
More from ABC News (Australia)
- The biggest market sell-off since 'Liberation Day' | The Business | ABC NEWS — Score: 50%
- Designer Katie Perry wins trademark case against pop star | ABC NEWS — Score: 50%
- A look around the NT as residents deal with flooding emergency | ABC NEWS — Score: 50%
- Bundaberg homes inundated after Burnett River peaks | ABC News — Score: 50%
- Reindeer races in Finland draw international crowds | The World | ABC NEWS — Score: 50%
- Grave fears for Iranian footballers after Australia asylum saga | The World | ABC News — Score: 50%