AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Collaboration & evaluation for LLM apps
Practical AI
The role of fine tuning in model adaptation
Less fine tuning than expected has been observed in the deployment of human loop back in 2022. Prompt engineering has shown to be powerful, and the need for fine tuning has shifted towards incorporating factual context into models rather than specific use cases. This has led to the emergence of retrieval augmented generation (RAG) as a effective solution. Fine tuning is now mainly required for optimizing cost, latency, and tone of voice, rather than for adapting the model to a specific use case. Its heavier operational demands, including the need for a specific dataset and longer processing time, make it a less common choice for adaptation.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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