Digg
@digg
New alpha:
参加 June 2008
577 フォロー中 1.1M ファン
Researchers say they decoded encrypted reasoning from @AnthropicAI, @OpenAI and @GoogleDeepMind by feeding it to weaker models from the same provider.
Co-author @DavidSchmotz says the flaw exposed personal data and credentials inside publicly shared session logs.
もっと見る
