[Funny] Just read the docs bro
Software Development and Programming Careers (Official Discussion Thread)
- Thread starter Blackking
- Start date
-
- Tags
- careers programming
Secure Da Bag
Veteran
From 2.0 GPA to $500k SE
I'd say no. You can look online but there are a lot of free courses out there that go over Prompt Engineering. I believe Google has one, Microsoft, Amazon etc.
Also look into vibe coding and best practices on Youtube for that. Programming and coding in general is being massively disrupted with what's going on with these AI vibe coding tools. You just have to understand how to get to an expected outcome through prompts. The more coding knowledge you have the better tho, but the barrier for developing and building things is being shattered.
Here's a great explainer on some of the engineering tools that are becoming standard for programming
I think there are people without IT related degrees who are doing it.
[Tutorials and Guides] Google just dropped a 68-page ultimate prompt engineering guide (Focused on API users)
Posted on Fri Apr 11 15:03:14 2025 UTC
/r/PromptEngineering/comments/1jws1ag/google_just_dropped_a_68page_ultimate_prompt/
Whether you're technical or non-technical, this might be one of the most useful prompt engineering resources out there right now. Google just published a 68-page whitepaper focused on Prompt Engineering (focused on API users), and it goes deep on structure, formatting, config settings, and real examples.
Here’s what it covers:
How to get predictable, reliable output using temperature, top-p, and top-k
Prompting techniques for APIs, including system prompts, chain-of-thought, and ReAct (i.e., reason and act)
How to write prompts that return structured outputs like JSON or specific formats
Grab the complete guide PDF here: Prompt Engineering
If you're into vibe-coding and building with no/low-code tools, this pairs perfectly with Lovable, bolt.new, or the newly launched and free Firebase Studio.
P.S. If you’re into prompt engineering and sharing what works, I’m building Hashchats - Chat with AI & People Together — a platform to save your best prompts, run them directly in-app (like ChatGPT but with superpowers), and crowdsource what works best. Early users get free usage for helping shape the platform.
What’s one prompt you wish worked more reliably right now?
/r/PromptEngineering/comments/1jws1ag/google_just_dropped_a_68page_ultimate_prompt/
Whether you're technical or non-technical, this might be one of the most useful prompt engineering resources out there right now. Google just published a 68-page whitepaper focused on Prompt Engineering (focused on API users), and it goes deep on structure, formatting, config settings, and real examples.
Here’s what it covers:
How to get predictable, reliable output using temperature, top-p, and top-k
Prompting techniques for APIs, including system prompts, chain-of-thought, and ReAct (i.e., reason and act)
How to write prompts that return structured outputs like JSON or specific formats
Grab the complete guide PDF here: Prompt Engineering
If you're into vibe-coding and building with no/low-code tools, this pairs perfectly with Lovable, bolt.new, or the newly launched and free Firebase Studio.
P.S. If you’re into prompt engineering and sharing what works, I’m building Hashchats - Chat with AI & People Together — a platform to save your best prompts, run them directly in-app (like ChatGPT but with superpowers), and crowdsource what works best. Early users get free usage for helping shape the platform.
What’s one prompt you wish worked more reliably right now?
Prompt Engineering Guide: The Ultimate Guide to Generative AI
Learn Prompting offers a comprehensive, free guide on Generative AI and Prompt Engineering, perfect for beginners and advanced users alike. Start your AI journey now!
Shot-Based Prompting: Zero-Shot, One-Shot, and Few-Shot Prompting
Learn about Shot-Based Prompting, a technique where you show the AI examples to guide output. Understand the benefits over zero- and one-shot prompts for better responses.
Just looking at the landscape right now, be selective with where you put hours into. You are not going to beat machines when it comes to development, programming and debugging etc...
Do some more research on the field before you go too deep.
Writing a good prompt is a great way to optimize interactions w/ LLMs, but IIRC, I have seen articles saying that efficient prompts will be ingrained into more powerful models. Here are some articles from this month (haven't read these specific ones yet but they might give you a better understanding)
Prompt Engineering Jobs Are Obsolete in 2025 – Here’s Why | Salesforce Ben
From a hot job to obsolete? Learn why Prompt Engineers are fading and discover the new AI roles that are gaining momentum.
www.salesforceben.com
Understanding prompt engineering and prompt design overall will become a standard skill that all professionals regardless of industry will have to have honestlyDo some more research on the field before you go too deep.
Writing a good prompt is a great way to optimize interactions w/ LLMs, but IIRC, I have seen articles saying that efficient prompts will be ingrained into more powerful models. Here are some articles from this month (haven't read these specific ones yet but they might give you a better understanding)
Prompt Engineering Jobs Are Obsolete in 2025 – Here’s Why | Salesforce Ben
From a hot job to obsolete? Learn why Prompt Engineers are fading and discover the new AI roles that are gaining momentum.
getting LLM's to improve your prompt is the real cheat code.
null
...
have you ever used an LLM to code anything complex? if so in what languages?
null
...
what does that mean?
To me, prompt engineering is like writing a SQL query or web-search: those skilled @ translating what they are trying to do into machine-friendly logical statements are good at finding the data they want... But, if queries are an exercise in logic, machines will always have greater 'logical' potential than humans, and IMO have a short runway to best the average human re: using logic to return data.
LLMs are getting increasingly better at using logic/probabilities (read:educated guesses?) to guess what we are trying to do. There's the simple stuff like understanding when we misspell/forget a word, but also the probabilistic stuff when it answers based on what is most probable... (On a related note, it is interesting to use 'thinking' models to
Obviously current models are not ready for it yet, but I do think that as models get better at contextualizing, it will negate the need for prompt-engineering. I don't disagree that it is very useful, I just have reservations about it being a standalone career-path beyond the near-term. I could be wrong tho
null
...
null
...
we don't know what you consider complex coding to be?
you didn't respond to this post :