The Pros (And Con) of Customizing Large Language Models

2 years ago thenewstack.io

Summary: This is a summary of an article originally published by The New Stack. Read the full original article here →

Before the artificial intelligence collective destroy humanity, it’s going to have to settle a few things in its own house first. Tabnine’s is team custom-trained, while its primary competitor — GitHub https://thenewstack.io/gpt-4-ai-powered-microsoft-security-copilot-arrives/ — is driven by the more broadly trained LLM https://thenewstack.io/30-non-trivial-ways-for-developer-to-use-gpt4/.

“Tabnine was the first AI code assistant on the planet,” Jung stressed to The New Stack in a recent interview.

“We may think general AI is magic, but at the end of the day it’s just machine learning,” he said.

There are tradeoffs in a custom trade model: You do have to know where you’ll be using the model, Jung said.

DevOps Articles