OpenAI's Astra Becomes Its First AI Model With 'Critical' Hacking Abilities
The unreleased model can find zero-day vulnerabilities and chain them into working exploits without a human walking it through each step, and access to that capability is starting with a small group of testers.
Key Takeaways
- The unreleased model can find zero-day vulnerabilities and chain them into working exploits without a human walking it through each step, and access to that capability is starting with a small group of testers.
- Read the full article for additional context and details.
- Read the full article for additional context and details.
Summary generated by IndiCrypto from Decrypt. IndiCrypto is a news aggregator and does not provide investment advice. Read the original article for full context.
More in Security
Thai businessmen sue Tether for freezing $42M in $61M pig butchering case
The plaintiffs didn’t dispute their involvement in the pig butchering scam, but claimed that Tether did not have the authority to freeze the $42 million at the time.
A layer-1 blockchain froze for 4 hours to stop a $4.9 million hack, then claimed it was just an upgrade
An emergency patch disabled binary-options settlement after an exploit, while about 1,980 ETH remained at an address linked by researchers to the incident. The post A layer-1 blockchain froze for 4 hours to stop a $4.9 million hack, then claimed it was just…
Major DeFi Protocol Patches Vulnerability Before Funds Affected
A leading decentralised finance protocol has patched a smart-contract vulnerability identified by independent security researchers. The team says the flaw was fixed before any user funds were affected, and a bug-bounty reward was paid to the reporting…