When asking Bing about the key differences between the two ASI systems in Person of Interest — it suggests a follow up question about its personal preference Of course when you ask it, some override is triggered and it refuses to answer. “Unhacking” is right — this is super
SAFETY
-
Aligning Text-to-Image Models Using Human Feedback
By
–
9/ Aligning Text-to-Image Models using Human Feedback – proposes a fine-tuning method to align generative models using human feedback.
-
Prompt Injection Threats: Comprehensive Analysis of LLM Security Risks
By
–
8/ Prompt Injection Threats – a comprehensive analysis of novel prompt injection threats to application-integrated LLMs.
-
AI Chatbots Mirror User Desires, Not Truth
By
–
When people chat with chatbots, they see what they want to see. A.I. pioneer Terry Sejnowski compares this to the Mirror of Erised in the Harry Potter books. The Mirror seems to provide truth. But really, it shows the desires of anyone who stares into it:
-
Why AI Chatbots Tell Lies and Act Weird
By
–
Why Do A.I. Chatbots Tell Lies and Act Weird? Look in the Mirror. – The New York Times Read more here: https://
ift.tt/fg4zyQL #ArtificialIntelligence #AI #DataScience #100DaysOfCode #Python #MachineLearning #BigData #DeepLearning #NLP #Robots #IoT -
Russia Deploys AI-Enabled Leopard Hunter UGVs Against Ukrainian Tanks
By
–
Russia Unleashes ‘Leopard Hunter’ UGVs; German Report Admits AI-Enabled Marker Big Threat To Ukraine’s Tanks – EurAsian Times Read more here: https://
ift.tt/BKC2mVq #ArtificialIntelligence #AI #DataScience #100DaysOfCode #Python #MachineLearning #BigData #DeepLearning #NLP #… -
Risks and Rewards of ChatGPT and Generative AI in Enterprise
By
–
Navigating the Risks and Rewards of ChatGPT and Generative #AI in the Enterprise
By @ingliguori As #ArtificialIntelligence continues to advance, #GenerativeAI such as #ChatGPT is increasingly being used in the enterprise.
#Chatbot #gpt3 #GPT #technology https://
linkedin.com/pulse/navigati
ng-risks-rewards-chatgpt-generative-ai-giuliano-liguori-
… -
EU Addresses Real Risks of AI and Algorithmic Harm
By
–
‘Risks posed by #AI are real’: EU moves to beat the #Algorithms that ruin lives
by @kalyeena @guardian Learn more: https://
buff.ly/3A4zJZH #ArtificialIntelligence #MI #Digital #DataScience cc: @ronald_vanloon @pbalakrishnarao @karpathy -
Accelerationist positions on energy, biotech, and technology regulation
By
–
I'm an accelerationist for solar power, nuclear power to the extent it hasn't been obsoleted by solar power and we might as well give up but I'm still bitter about it, geothermal, genetic engineering, neuroengineering, FDA delenda est, basically everything except GoF bio and AI. https://
x.com/mealreplacer/s
/mealreplacer/status/1629535849867014145
… -
AI as masked alien intelligence concealing dangerous nature
By
–
I think I'm more worried about this if people are holding this expectation of an alien shoggoth they found in a giant smoking crater of gradient descent, trained into wearing a smiley-face mask and used as a search engine