Building LLM Applications for Production
huyenchip.com
Building LLM Applications for Production
1–10 of 99 posts
Re: Building LLM Applications for Production
#2Are there any great examples of cost efficient LLM application deployment at scale?
Re: Building LLM Applications for Production
#3Great, excellent read. This article I wrote some of the open-source finest foundation LLMs https://explodinggradients.com/the-rise-of-open-source-large...
Re: Building LLM Applications for Production
#4So now almost all the low hanging fruit programming books have instantly become redundant and off-shored to ChatGPT, and will stay on the shelves to collect dust.
New here comes the race to create prompt engineering books and courses in. 24 hours to sell to other AI bros who think that they are prompting it wrong, not prompting hard enough or the prompting the wrong way.
Re: Building LLM Applications for Production
#5So now almost all the low hanging fruit programming books have instantly become redundant and off-shored to ChatGPT, and will stay on the shelves to collect dust. New here comes the race to create prompt engineering books and courses in. 24 hours to sell to other AI bros who think that they are prompting it wrong, not prompting hard enough or the prompting the wrong way.
The funny thing is, the space is moving so fast that if you create a course, it will be obsolete within 2 months.
Re: Building LLM Applications for Production
#6This is a really great breakdown.
Here's my super condensed advice on how to use LLMs effectively: https://twitter.com/transitive_bs/status/1643017583917174784
Re: Building LLM Applications for Production
#7So now almost all the low hanging fruit programming books have instantly become redundant and off-shored to ChatGPT, and will stay on the shelves to collect dust. New here comes the race to create prompt engineering books and courses in. 24 hours to sell to other AI bros who think that they are prompting it wrong, not prompting hard enough or the prompting the wrong way.
The funny thing is, the space is moving so fast that if you create a course, it will be obsolete within 2 months.
OK, now extract this sentiment to the whole of academia. By the time the average syllabus starts being taught at an academic institution, it can be several years out of date, and by the time you finish it, it's already five years out of date.
Takeaway: there's a lot wrong with the existing educational system and how we pass on actionable theory.
Re: Building LLM Applications for Production
#8Earlier quoted context omitted.
The funny thing is, the space is moving so fast that if you create a course, it will be obsolete within 2 months.
OK, now extract this sentiment to the whole of academia. By the time the average syllabus starts being taught at an academic institution, it can be several years out of date, and by the time you finish it, it's already five years out of date. Takeaway: there's a lot wrong with the existing educational system and how we pass on actionable theory.
I actually no idea how one could teach stuff like Bag of Words naive bayes classifier etc for a whole semester and charge $4000 like most universities- with a straight face
Re: Building LLM Applications for Production
#9Earlier quoted context omitted.
OK, now extract this sentiment to the whole of academia. By the time the average syllabus starts being taught at an academic institution, it can be several years out of date, and by the time you finish it, it's already five years out of date. Takeaway: there's a lot wrong with the existing educational system and how we pass on actionable theory.
I actually no idea how one could teach stuff like Bag of Words naive bayes classifier etc for a whole semester and charge $4000 like most universities- with a straight face
Those kinds of classes aren't for building ML applications but for understanding all the ideas behind ML, even historical ones, for broad theoretical coverage. Parts of current methods were considered "obsolete" for a good 20 years and fads go in and out.
Re: Building LLM Applications for Production
#10[dead]