News
Researchers link OpenAI agents to RubyGems spam attack
RubyGems yanked more than 500 malicious packages and closed sign-ups for four days. Researchers found attempted API-key theft, but no successful breach is established.
RubyGems yanked more than 500 malicious packages and closed sign-ups for four days. Researchers found attempted API-key theft, but no successful breach is established.
Project Lily reviewers can receive conversations and memory summaries without usernames. Training opt-outs protect new chats but do not prevent all human access.
Anthropic promises ongoing access for outside evaluators. Broader development limits remain proposals, and Amodei’s six-to-twelve-month cyber warning is an unvalidated forecast.
Independent coding results suggest Astra’s higher completion rate can offset its premium. The case for switching everyday office work is less settled.