3min 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

RAG Is A Hack - with Jerry Liu from LlamaIndex

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

NOTE

Fine-tune New Knowledge into LLMs

New knowledge can potentially be found through algorithms, despite some disagreement on the topic./nOpenAI's fine-tuning endpoints have limitations when it comes to memorization and next token production./nTraining a transformers model yourself may allow for better results compared to using the open AI API./nGorilla, a model trained to use specific APIs, utilizes prior learning and retrieval to enhance performance./nRag is currently the default method for augmenting knowledge, but there are questions regarding the extent to which it can internalize concepts and details./nBaking everything into the training process of a language model offers some advantages in terms of knowledge integration./nThe lack of knowledge on how to effectively implement the approach, along with cost considerations, hinders its current usage.

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