I didn’t want to mindwipe an LLM until now. 🙂
SAFETY
-
Regulatory Frameworks for Trustworthy AI Integration
By
–
Emerging regulatory frameworks like the #OSTP AI Bill of Rights and #NIST AI Risk Management Framework aim to address trust, safety, and ethical concerns with #AI. Global AI Ethicist, @HaniyehMah, shares her insights on how to integrate a trustworthy AI framework into the AI
-
Domino Model Sentry: Responsible Enterprise AI Solution
By
–
Excited to introduce Domino Model Sentry! Navigate #AI complexities responsibly with accuracy, fairness & transparency. Explore our breakthrough solution for #EnterpriseAI: https://
domino.buzz/3OZaobr #ResponsibleAI -
Cruise driverless cars struggle with SF traffic and turns
By
–
Your @Cruise correspondent: Taking many SF rides at night, fully driverless. Routes through empty quiet blocks: good. Three lanes of traffic on Franklin: lots of braking and veering, way worse than any Uber driver. Left turns at speed with traffic: close calls with parked cars.
-
LEACE: Perfect Linear Concept Erasure in Closed Form
By
–
LEACE: Perfect linear concept erasure in closed form paper page: https://
huggingface.co/papers/2306.03
819
… introduce LEAst-squares Concept Erasure (LEACE), a closed-form method which provably prevents all linear classifiers from detecting a concept while inflicting the least possible damage to -
Large Language Models Struggle With Code Containing Potential Bugs
By
–
Large Language Models of Code Fail at Completing Code with Potential Bugs paper page: https://
huggingface.co/papers/2306.03
438
… Large language models of code (Code-LLMs) have recently brought tremendous advances to code completion, a fundamental feature of programming assistance and code -
Deductive Verification of Chain-of-Thought Reasoning in Large Language Models
By
–
Deductive Verification of Chain-of-Thought Reasoning paper page: https://
huggingface.co/papers/2306.03
872
… Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive -
Prompt Injection Explained with Video Slides and Transcript
By
–
Prompt injection explained, with video, slides, and a transcript https://
bit.ly/41U1KxC -
Moving Beyond AI Doomerism Toward Real Risk Analysis
By
–
https://
venturebeat.com/ai/apocalyptic
-panic-and-ai-doomerism-need-to-give-way-to-analysis-of-real-risks/
… -
Deepfakes AI threat to intelligence democracy requires urgent action
By
–
and Andy Makridis, former COO of the CIA, highlighted on our last panel with Chairman Mac Thornberry, Michèle Flournoy, and @LeeHudson_
: Our intelligence agencies, and democracy broadly, are going to need to confront the enormous problem of deepfakes and AI-powered