You already use prompting every day.
You just don't know the names of what you're doing.
Every time you type "fix this error" into ChatGPT or "re...
For further actions, you may consider blocking this person and/or reporting abuse
💡 Funny how a Deep Learning exam ended up teaching me techniques I now use in my everyday AI workflows!
These aren't just exam notes anymore — they're practical lessons I've picked up and started applying while building projects.
Which prompting technique has made the biggest difference in your AI workflow? 👀
Great Reading dude, i have also wrote an article on this dev.to/taqui/why-your-llm-prompts-...
In the 3rd section i have discussed about something really cool that you might need to know:)
Read it! Cool. Its one of the reasons, writing a system prompt takes a lot of time testing and trying to break it yourself. I've been there.😅
I've done it for a lot of projects.
Have A Great Day!
Which one stuck with you most once the exam was over?
So, I realized I use:
Format specific when you integrate AI wrapper feature to you project, and most of the times make sure it returns proper JSON output.
And probably mix of chain of thought and GK for exam prep.
Also, role playing used to be popular when chatbots were new. Now almost nobody uses it.
How about you, you seem more experienced, your thought would be more valuable than mine, Sir.😅
In the authentication documentation example, I'd have the first pass label each step as observed in the code, inferred, or still unknown. Asking for a list first can organize an explanation, but it can also turn an invented middleware or redirect step into a convincing foundation for the next answer. Pairing that list with file references and one captured login trace gives the documentation pass something external to check. I'd also include a failed login and an expired session, so the final write-up covers more than the happy path.
That's a great way to use notes. Keep going bro!
Really!
Thanks bro!😄
Great Job! Really useful explanation, thx for sharing
Hello 👋🏻
Hi!
Naming the techniques is oddly useful — once you can point at “this is chain-of-thought vs role priming,” it’s easier to notice which habit actually moves the answer and which one is just filler.
Hey, this article appears to have been generated with the assistance of ChatGPT or possibly some other AI tool.
We allow our community members to use AI assistance when writing articles as long as they abide by our guidelines. Please review the guidelines and edit your post to add a disclaimer.
Failure to follow these guidelines could result in DEV admin lowering the score of your post, making it less visible to the rest of the community. Or, if upon review we find this post to be particularly harmful, we may decide to unpublish it completely.
We hope you understand and take care to follow our guidelines going forward!
Guys, this content is from coursework given in college. It's not AI generated.🥲😑
It is referring to the how the post was written...
Can it be the case that PDFs given were AI generated? But I wrote everything other than examples by myself.
Other part was from Pdfs.
No worries, my bad the pdf itself seems AI generated!😭
Sorry!
No worries!