Only need a couple H100s, directly on HF
GENERATIVE AI
-
AI Applications in Product and Project Management
By
–
How about with regards to product/project management?
-
Reconsider AI Evaluation Metrics for Code Generation Capabilities
By
–
if you consider autonomously writing 800LOC of C code from very simple instructions as "didn't work" you may wish to reconsider the nonlinearity of your evals. be well.
-
Using Udio for AI-generated music creation
By
–
In case you haven't tried it yet, @udiomusic is worse testing. It takes some time to generate a song but the output is quite good. Listening to my own album about cyberpunk hackers already for a while 🤖🎧 pic.twitter.com/0LadBQLdAs
— 🚨 AI News | TestingCatalog (@testingcatalog) 10 avril 2024In case you haven't tried it yet, @udiomusic is worse testing. It takes some time to generate a song but the output is quite good. Listening to my own album about cyberpunk hackers already for a while
-
New Quick Post Feature Generates Posts Using Writing Style
By
–
I gave the "every day is not a good day" prompt to our new Quick Post feature in http://
Reactor.is (coming out to the beta group in just a few days. Here's the post it wrote with no other input other than my writing style "writeprint" that gets automatically added to -
Building AI Tools: Managing Model Mistakes and Reliability
By
–
Not at all. I'm building tools that work against multiple models, I'm happy to leave the detailed evals to other people. I'm going to tell my users that they should assume that AI makes mistakes all the time, because that's a pretty good rule of thumb for everything!
-
Model Scale Determines Agent Brain Performance and Capability
By
–
This is a key point on AI agents "Brains" matter for agents. As long as the scaling law holds, you get much better results out of using bigger frontier models as the main brains of your agent, though it might be able to delegate to lesser AIs Labs with the best model get the
-
GPT-2 as Ideal Class Project for Educational Book
By
–
GPT-2 turns out to be a perfect class project for that book (which I really like and own)
-
Explaining LLM.c: Simplifying Large Language Model Training
By
–
# explaining llm.c in layman terms Training Large Language Models (LLMs), like ChatGPT, involves a large amount of code and complexity. For example, a typical LLM training project might use the PyTorch deep learning library. PyTorch is quite complex because it implements a very https://
t.co/dkpZGRvkmU -
Free API token limits and cost implications analysis
By
–
… but the 32,000 tokens per minute presumably prevents free API calls from using more than 32,000 tokens? If so max cost would be 22 cents per call for input, so a lot less expensive overall