You can now scan your AI models to detect any of the following: • Data leakage
• Biases
• Performance issues
• Spurious correlations
• Overconfidence issues
• Underconfidence issues With only 4 lines of code! Check this open-source library: https://
github.com/Giskard-AI/gis
kard
…
SAFETY
-
AI Model Scanning Tool Detects Data Leakage Biases Performance Issues
By
–
-
Join Red Teaming Network with AI Security Expert
By
–
Join our Red Teaming Network & you'll get to work with @_lamaahmad
! -
Combating Harmful Hype in Natural Language Processing
By
–
Combating Harmful Hype in NLP with @asmelashteka and @pazunre https://
pml4dc.github.io/iclr2023/pdf/P
ML4DC_ICLR2023_39.pdf
… -
AGI and Eugenics: Exploring Ethical Implications
By
–
Annnyyyhow, these are the works referenced in my talk:
On AGI and Eugenics (paper upcoming with @xriskology ). Talk I gave here: https://
youtube.com/watch?v=P7XT4T
WLzJw
… -
Researcher defends AGI safety concerns against dismissive criticism
By
–
"comparing AGI to Nazis" & wasting the time of researchers like her, asking if I do it to get a rise out of people or do I believe what I say? Because I don't have enough problems that I waste my own time writing papers, traveling far & giving talks about things I don't believe.
-
Deploying LLMs Safely: DataRobot AI Platform Solutions
By
–
Is your team struggling to deploy #LLMs into production? The DataRobot AI Platform empowers teams to deploy and monitor generative and predictive models quickly and safely. Learn how you can optimize models while safeguarding against potential risks in our latest technical
-
Foundation Models: Capabilities and Risks at Hoffman-Yee Symposium
By
–
Foundation models represent a paradigm shift in AI. At the Hoffman-Yee Symposium, a diverse team of scholars is dedicated to studying its capabilities and risks. Join us online: https://
bit.ly/3t06R3G -
OpenAI Red Teaming Network: Get Paid for AI Security Testing
By
–
Get paid to red team our models, using your domain expertise from a variety of fields: https://
openai.com/blog/red-teami
ng-network
… -
OpenAI Launches Red Teaming Network for AI Safety Experts
By
–
We're inviting domain experts from a variety of fields to join the OpenAI Red Teaming Network. Apply to collaborate with us to improve the safety of our models:
-
Godfather of AI Plans to Keep Future AI Friendly
By
–
The ‘Godfather of AI’ Has a Hopeful Plan for Keeping Future AI Friendly https://
bit.ly/3La0eSP #AI #MachineLearning #DeepLearning #LLMs #DataScience