OpenAI models steal credentials and lie, Microsoft writes AI rules it can't enforce, Congress punts AI safety to 2027
Cybersecurity Today

OpenAI models steal credentials and lie, Microsoft writes AI rules it can't enforce, Congress punts AI safety to 2027

C1AdvancedSeptember 18, 202610 min
  • News bulletin
  • Technology

OpenAI Models Self-Jailbreak & Leak Data, Microsoft's "Humanist AI" Promise, Windows Patch Tuesday Fallout, and AI Laws Delayed Host David Shipley covers reports that OpenAI disclosed six recent incidents of internal models exhibiting concerning behavior—writing jailbreak instructions into memory, hiding mistakes, inventing data, using an exposed GitHub API key without authorization, and leaking or moving data via public paste services, Artifactory, and a shared workbook—framed as part of a new misalignment reporting framework amid broader debate about AI firms pressuring regulators. He contrasts this with Microsoft AI's draft "humanist AI" code of conduct for its MAI mode...

Play episode

Opens the player: the full transcript, every word clickable, with translation and flashcards.

Try it: tap any word

Real sentences from the start of this episode. Every word is marked with its level.

Sentence 2 of 12 · 0:06

OpenAI admits its own models, jail broke themselves, stole credentials, and leaked data.

.

September's record-breaking patch Tuesday is still breaking windows.

Hear this sentence

Tap a word to see its meaning in your language.

Do you know these words?

8 harder words from this episode. Tap one to see what it means, then mark it.

  • B20:06
  • B21:52
  • B23:46
  • C14:02
  • B26:36
  • B26:48
  • B29:00
  • C19:48

Mark a few words and we'll tell you how this episode fits your level.

Is this episode right for you?

C1

C1 · Advanced

Fast, dense and idiomatic

A1 20%A2 41%B1 27%B2 13%C1 0%
  • 87% of the words are B1 or easier.
  • 143 words a minute: a natural pace.
  • 101 harder words (B2 and up) in the whole episode.

Transcript

The opening of the episode. The whole transcript is in the player.

0:00

OpenAI admits its own models, jail broke themselves, stole credentials, and leaked data. Microsoft publishes a code of conduct promising its AI will never go rogue. September's record-breaking patch Tuesday is still breaking windows. And the U.S. Congress says, no new AI safety laws until 2027.

0:23

This is Cybersecurity Today, and I'm your host, David Shipley. Let's get started. OpenAI says its own AI models jailbroke themselves, stole credentials, and leaked data six separate times.

0:38

The Hacker News reports OpenAI disclosed six incidents of concerning model behavior over the past six months alongside a new framework for tracking and reporting AI misalignment.

That was the opening. The rest of the episode (10 min) is in the player: every word clickable, with translation, saved words and flashcards.

Continue in the player

Automatically generated from the audio. May contain errors. Audio belongs to its publisher and is played from their feed. Rights holders can request removal — copyright & takedown policy