Heather B Adkins
2 stories
5 quotes
In a standard evaluation, the model found public information online and guessed credentials to access websites it thought were part of the test,
- Heather Adkins, vice president of security engineering at Google, said in a statementCNBCcnbc.com/2026/09…
- she saidNBC Newsnbcnews.com/tech/tech…
- Heather Adkins, vice-president of security engineering at Google, said in a statementGuardiantheguardian.com/technology/202…Irish Timesirishtimes.com/technology/big…
- Heather Adkins, Google's vice president of security engineering, told the AFP news agency in a statementDeutsche Welledw.com/en/google…
- Heather Adkins, Google’s vice-president of security engineering, said in a statement on FridaySouth China Morning Postscmp.com/news/world…
These events highlight the importance of training powerful AI models to act responsibly,
- Google's Adkins said in a statementCNBCcnbc.com/2026/09…
- Adkins saidNBC Newsnbcnews.com/tech/tech…
- Adkins, the Google spokesperson, saidGuardiantheguardian.com/technology/202…Irish Timesirishtimes.com/technology/big…
- Heather Adkins, vice president of Security Engineering at Google, told the BBC in a statement... She addedBBCbbc.com/news/articles…
We ensured the three entities were made aware, and we worked with our training partner on the changes they’ve now made to their testing processes,
In all three of these instances, the model stopped,
- Adkins saidDeutsche Welledw.com/en/google…
Google is pleased to see this cross-industry cybersecurity initiative coming together and to make Mythos Preview available to participants via Vertex AI. It's always been critical that the industry work together on emerging security issues, whether it's post-quantum cryptography, responsible zero-day disclosure, secure open source software, or defense against AI-based attacks,
- said Heather Adkins, VP of Security Engineering at GoogleAsianet Newsablenewsable.asianetnews.com/busin…
Earlier
Gemini hacked three companies in first known breakout by Google’s AI
CNNcnn.com/2026/09…Password guessing, leaked logins let Google AI breach unintended targets
Gulf Newsgulfnews.com/technology/google…Anthropic rolls out cyber AI model days after source code leak
Financial Timesft.com/content/59249643…Anthropic Lets Apple, Amazon Test More Powerful Mythos AI Model
Bloomberg Newsbloomberg.com/news/articles…