![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
"A Mathematical Framework for Transformer Circuits"
Anthropic AI is an organization which has been created approximately a year ago by former OpenAI people who (I believe) have been unhappy about the current direction of OpenAI.
"Anthropic is an AI safety and research company that’s working to build reliable, interpretable, and steerable AI systems. Large, general systems of today can have significant benefits, but can also be unpredictable, unreliable, and opaque: our goal is to make progress on these issues."
They have just published their first major paper directed towards better understanding of Transformers. I am going to accumulate various links in the comments.
"Anthropic is an AI safety and research company that’s working to build reliable, interpretable, and steerable AI systems. Large, general systems of today can have significant benefits, but can also be unpredictable, unreliable, and opaque: our goal is to make progress on these issues."
They have just published their first major paper directed towards better understanding of Transformers. I am going to accumulate various links in the comments.
no subject
https://twitter.com/ch402/status/1473697352313679876 thread
https://twitter.com/nelhage/status/1473699073924513811 thread
https://twitter.com/ch402/status/1473710366874128393 thread
https://twitter.com/catherineols/status/1473728322181939205 thread
it so happened that Twitter for some reason alerted me to this thread, and that's how I learned about it:
https://twitter.com/ThomasMiconi/status/1474091696916860950