Extracting Real Training Data from ChatGPT

Extracting Real Training Data from ChatGPT

...And we are back with more AI related news, updates and insight into the impact AI is making to tackle global grand challenges.

---

Packed inside

  • Extracting Training Data from ChatGPT - adversarial attacks
  • Can Generalist Foundation Models Outcompete Special-Purpose Tuning?
  • and Home Monitoring of Asthma Exacerbations in Children and Adults with AI

If you are enjoying this content and would like to support the work then you can get a plan here from £2/month!

__________________________________

Key Recent Developments

---

UK to invest £500M more in AI compute capacity, launch five new quantum projects

What: The U.K. government will invest £500 million, or $626 million, to provide local researchers and organizations with access to compute capacity for artificial intelligence projects.?

---

Extracting Training Data from ChatGPT

Abstract: We have just?released a paper?that allows us to extract several megabytes of ChatGPT’s training data for about two hundred dollars. (Language models, like ChatGPT, are trained on data taken from the public internet. Our attack shows that, by querying the model, we can actually extract some of the exact data it was trained on.) We estimate that it would be possible to extract ~a gigabyte of ChatGPT’s training dataset from the model by spending more money querying the model.

__________________________________

AI Ethics and 4 good

?? Deep generative modeling of the human proteome reveals over a hundred novel genes involved in rare genetic disorders

?? Home Monitoring of Asthma Exacerbations in Children and Adults With Use of an AI-Aided Stethoscope

Other interesting reads

?? Dell Inks $150 Million Hardware Deal With AI Startup Imbue

?? Interview: Sam Altman on being fired and rehired by OpenAI

?? Google AI and robots join forces to build new materials

Papers

??Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine [Microsoft]

??Researchers at UC Berkeley Introduced RLIF: A Reinforcement Learning Method that Learns from Interventions in a Setting that Closely Resembles Interactive Imitation Learning

__________________________________

Cool companies found this week

Foundation Models

Imbue - Building AI systems that can reason

__________________________________

__________________________________

Thanks for reading and we'll see you next week!

If you are enjoying this content and would like to support the work then you can get a plan here from £2/month!

___________________________________

www.nural.cc


要查看或添加评论,请登录

Marcel Hedman的更多文章

社区洞察

其他会员也浏览了