I think that will be very possible soon! We continue to write about it publicly :) Also thanks to my friends and colleagues who write a lot on this subject that I frequently collaborate with:
Really good article. I was discussing this with Shreya (the author), and an interesting insight was that prompting a LLM to follow these instructions do not work reliably.
I’ve had similar frustrations. Maybe the next thing to try is fine tuning? Curious what others think.
I am a python developer who has been envious of modern application dev frameworks
& typescript, but never had the time to invest in another stack. This is so exciting. I suspect this might be catalyst that empowers more people to ship stuff
Hi I'm Hamel, author of this blog post. A few months ago, I hosted a course on applied-llms that went viral https://maven.com/parlance-labs/fine-tuning and became a conference organically with 30+ speakers.
I thought it would be tragedy if this material were perpetually locked behind a paywall, so I worked hard to curate all the talks and make it freely available to everyone. I hope it is beneficial to everyone.
Hi Hamel, thanks for releasing this. Slightly OT, but do you have any advice for someone who wants to work on/with LLMs at a tech company? How can a fullstack engineer transition to work on LLMs? How do I get the attention of some of the good tech companies since they usually want some ML related roles on the resume? What sort of projects can I work on? Maybe blogging about my learning might help? I know this is a very generic question, but any advice from someone like you would be great!
Amazing contribution Hamel, thanks for sharing. I though it was behind a paywall as you said, very glad you decided to open it. Looking forward to start with this course.