Join devRant
Do all the things like
++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatar
Sign Up
Pipeless API
From the creators of devRant, Pipeless lets you power real-time personalized recommendations and activity feeds using a simple API
Learn More
-
what did you expect? Things are moving so fast maybe a little too fast
By the way, congratulations on becoming an "LLM Developer/Maintainer". A few years later, your resume would read "Developer with expertise in as many LLMs as you could count"
But yeah. I understand the comfort the regular development jobs bring us -
Select a toolset and a model to use and stick to it until you got the POC working. You can then reevaluate the field and change things or not. Also try to use a local model instead of a service so you can freeze the state of the AI between product iterations and don't have to deal with sudden behavior changes.
-
@ars1 without giving too much details, the client wants a chatbot that asks several questions and produces a downloadable report at the end.
-
@Oktokolo that's great recommendation. Thanks.
This trend is becoming really annoying really fast…
Bitmap.GetPixel isn't AI lmao
It remembers me of the "...
I got a job where I should develop a product based on LLMs.
Expectation: oh right! I'll be working with state of the art technology! 😀
Reality: badly documented libraries that are always changing; new libraries becoming obsolete in less than a month; my product ideas were done by somebody else twice before I could finish a POC; getting dizzy trying to keep up with the latest news about LLMs 😵💫
I think I want to do basic old boring stuff again. 😐
rant
gpt
llm
chatgpt