4min snip

Latent Space: The AI Engineer Podcast — Practitioners talking LLMs, CodeGen, Agents, Multimodality, AI UX, GPU Infra and all things Software 3.0 cover image

The End of Finetuning — with Jeremy Howard of Fast.ai

Latent Space: The AI Engineer Podcast — Practitioners talking LLMs, CodeGen, Agents, Multimodality, AI UX, GPU Infra and all things Software 3.0

NOTE

Can you fine-tune new information into a pre-trained model?

You can fine-tune new information into models, as fine-tuning is essentially the same as pre-training. However, we are not good at it because everyone does it differently. Even small models can have impressive capabilities, like generating SQL or coding snippets. There are good models in the 1 to 2 B range, but their performance evaluation is inconsistent. Fine-tuning can be useful for repetitive tasks in an enterprise setting. Smaller models have advantages in terms of resource usage, but their trustworthiness for certain tasks is questionable.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode