No Train No Gain:Revisiting Efficient Training Algrthm for Transformer-BasedLMarxiv.org11 points·by froster·3 anni fa·1 comments
Ask HN: For ML work. Is ChatGPT 4 is worth it? Which another LLM?1 points·by froster·3 anni fa·3 comments
Show HN: Innovative startup working on 3D Stem Learninginspiritvr.com1 points·by froster·4 anni fa·0 comments
Ask HN: What true thing do you believe that few people agree with you on?2 points·by froster·4 anni fa·6 comments
Ask HN: What is going on the Internet that everyone should be aware of?2 points·by froster·4 anni fa·2 comments
froster·3 anni fa·discussRecent paper highlights the difficulty of creating a new optimizer as drop-in replacement. Sophia and Lion were recently proposed as superior alternatives to Adam, but appeared worse in an independent eval
froster·3 anni fa·discuss"GPT4 should be reserved for tasks that nothing else can handle" which tasks?
froster·4 anni fa·discussNo, I'm not a marketer, I'm a tech student. I just want to know your perspective on this. That is why I'm asking.