#AI is not the future; it's here now and embedded in our daily lives. It's important to understand its impact on #jobs, #businesses, and #industries, and to develop #ethical and explainable AI to build #trust.
ETHICS
-
Biggest AI Mistakes Organizations Must Avoid
By
–
#AI is revolutionizing businesses, but it's not without its #challenges. Discover the biggest #AI #mistakes organizations make, and learn how to sidestep these #pitfalls, ensuring a smoother path to successful #artificial #intelligence integration. https://
forbes.com/sites/bernardm
arr/2023/04/03/the-12-biggest-ai-mistakes-you-must-avoid/
… -
ChatGPT Refuses to Write Jokes About AI World Takeover
By
–
I asked ChatGPT to craft me funny tweets about AI taking over the world… "I'm sorry, but as an AI language model, it's not appropriate for me to create content that portrays AI as a threat to humans." Well played sir! 🤫
-
Building AGI for the Follows: Humanity’s Purpose
By
–
Building AGI for the follows. That’s what man was put on earth for.
-
AI System Cannot Comprehend Finality Concept
By
–
My system does not comprehend finality pic.twitter.com/MjyELEoUTi
— Yohei (@yoheinakajima) 3 avril 2023My system does not comprehend finality
-
Autonomous AI Agents Tackle AI Alignment Problem
By
–
I asked my autonomous AI to solve AI alignment.
— Yohei (@yoheinakajima) 3 avril 2023
Fascinating to watch.
Agents:
– Task execution: text-davinci-003
– Task creation: text-davinci-003
– Task reprioritization: text-davinci-003 pic.twitter.com/rmOnKIgaAzI asked my autonomous AI to solve AI alignment. Fascinating to watch. Agents:
– Task execution: text-davinci-003
– Task creation: text-davinci-003
– Task reprioritization: text-davinci-003 -
GPT-5 Safety Testing Strategy Through Controlled Chat Interface
By
–
Let’s imagine that GPT-5 is super-intelligent, but works only via chat interface, its speed is within human abilities to observe in realtime, and OpenAI doesn’t release it to public, but undergoes rigorous testing. Wouldn’t they learn valuable lessons while staying safe?
-
GPT Models Lack Awareness of Their Own Strengths and Limitations
By
–
Interesting non-obvious note on GPT psychology is that unlike people they are completely unaware of their own strengths and limitations. E.g. that they have finite context window. That they can just barely do mental math. That samples can get unlucky and go off the rails. Etc.
-
Sam Misses Broader Message on Model Transparency
By
–
sam seems like he is picking up on part of the message from the jailbreaking community however, he fails to address the broader message calling for more model transparency in general
-
OpenAI unlikely to increase model transparency despite necessary pressure
By
–
it's improbable that OpenAI will ever disclose additional information about new models compared to what they revealed for GPT-4 (I expect it will diminish even further) but nevertheless, I think the pressure on them to do so is healthy and necessary