Using https://
platform.openai.com/docs/guides/fi
ne-tuning
… ? What have you used that for – I've not heard many examples of people fine-tuning 3.5
@simonw
-
Fine-tuning GPT-3.5: Use Cases and Community Experiences
By
–
-
Meta AI Launches Llama 3 with Search and Summarization
By
–
If you just want to try it as a user https://
meta.ai is running Llama 3 with the ability for it to execute and summarize searches -
Llama 3 API Search Capabilities vs Perplexity Sonar
By
–
I've not see a Llama 3 API with built in search capacity yet – @perplexity_ai have sonar-medium-online but I think that's Mixtral 8x7B? They might upgrade to a Llama 3 online model soon though
-
Fine-tuning vs RAG: When to Use Each Approach
By
–
That's not the same as believing that fine tuning can't teach a model new knowledge under any circumstances – but in practice many people I see who think they need to fine tune a model would be better off using RAG instead
-
RAG vs Fine-tuning for Small Document Loading
By
–
My understanding is that if you want to eg load your company employee handbook (~20 page PDF) into a model you're likely to get much better results with RAG than with fine-tuning – can you fine tune such that the model reliable answers questions about something that small?
-
Design Skills Transform LLM Interface Beyond Chatbot Model
By
–
I also love this as an example of what happens when someone with design skills builds an interface to an LLM tool that's not Yet Another Chatbot
-
Structured Data Extraction from Images Using Claude 3 Opus
By
–
Beautiful example here of structured data extraction from an image using Claude 3 Opus – most of the LLM implementation is handled by this tools schema: https://
github.com/timpaul/form-e
xtractor-prototype/blob/main/data/extract-form-questions.json
… -
Scaling Instances in Parallel: Infrastructure vs Engineering Tradeoffs
By
–
Can you run more instances in parallel? Probably cheaper to pay for 5x the servers than to engineer a new solution Might also be worth trying out Playwright, it's effectively Puppeteer 2.0 at this point
-
AI Applications for Data Extraction and Document Question Answering
By
–
Interesting how little overlap there is between that list and my own preferred applications – I guess structured data extraction falls into "data entry", but answering questions against a document is harder to categorize – I guess it's "Jumping to the useful info"
-
Person of Interest Predicted Snowden Surveillance Revelations
By
–
Yeah Person of Interest had their Snowden episode a year before Snowden happened https://
newyorker.com/culture/cultur
e-desk/person-of-interest-the-tv-show-that-predicted-edward-snowden
…