Clearly LLMs must one day run in Space Step 1 we harden llm.c to pass the NASA code standards and style guides, certifying that the code is super safe, safe enough to run in Space. https://
en.wikipedia.org/wiki/The_Power
_of_10:_Rules_for_Developing_Safety-Critical_Code
… (see the linked PDF)
LLM training/inference in principle should be super
COMPUTING
-
LLMs in Space: Hardening llm.c to NASA Safety Standards
By
–
-
Building a Different Web: Alternative Digital Future
By
–
On the same theme, this is even better https://
citationneeded.news/we-can-have-a-
different-web/
… -
Implementing Ollama Llama-3 Model Locally with Context
By
–
6. Define a function to call the Ollama Llama-3 model locally with context.
-
Excel Needs Version Control and Automated Testing
By
–
(That said, if Excel had proper version control and widely spread robust patterns for automated testing the world would run a whole lot smoothly)
-
Spreadsheets as Legitimate Sophisticated Software Development
By
–
Completely disagree with you there. I've seen plenty of examples of spreadsheets that absolutely count as sophisticated software development
-
1 Trillion Edges: Breakthrough in AI Model Architecture
By
–
An edgy post… 1 trillion edges, in fact! https://t.co/ymbl16TL2X
— Jeff Dean (@JeffDean) 1 mai 2024An edgy post… 1 trillion edges, in fact!
-
Google Cloud Architect Certification Achievement Announced
By
–
I am delighted to know that I have been awarded Cloud Architect – Google Cloud Certified Professional #CloudComputing #goohke #cloudarchitech @googlecloud @Google
-
MATLAB and Simulink Historical Documentation Archives Discovery
By
–
Found in the archives…MATLAB and Simulink prints
-
Groq CEO discusses fast token generation and AI expansion plans
By
–
Chatting with @GroqInc
’s CEO @JonathanRoss321
. Groq has super fast token generation capabilities now. And, I was excited also to hear about his plans to scale up capacity aggressively and also expand this to other models than just LLMs! This is a good time to be building AI