allpaca
Re:Open Letter to Meta by Mozilla
on Thursday May 02, 2024 @07:09AM (#40234813)
This is extremely important. I'm sided with Mozilla
Adapt-LLM: LLM That Decides If to Retrieve External Information or Not
Re:Speeding up C++ build times
on Sunday April 28, 2024 @07:34PM (#40192975)
C++ is evolving so much, however I don't understand this thing: why people continue to develop AI projects with Python? I'd choose C++ instead...
Cognita: Retrieve Information from Documents with RAG
Re:AI-powered cameras installed on Metro buses to ticket illegally par...
on Sunday April 28, 2024 @04:36PM (#40191597)
Because it's trendy, obviously.
Re:Can we tell the difference between human-written and GPT-4-written ...
on Sunday April 28, 2024 @03:53PM (#40191299)
There are some terms that LLMs use a lot (delve, dive, foster, etc...), but if you're smart enough you can replace them with synonyms... Also, LLMs tend to create short sentences, but you can merge two consecutive sentences in a simple way, with a however, in fact, etc...
Re:LoRA+: Efficient Low Rank Adaptation of Large Models
on Sunday April 28, 2024 @01:44PM (#40190312)
Can you tell us more about it? Have you reported the results of your experiments in a post?
Re:LoRA+: Efficient Low Rank Adaptation of Large Models
on Sunday April 28, 2024 @01:42PM (#40190301)
This is old, having been released in February... Why do you talk about it now?