While it's possible to see gains in complex problems through brute force, learning more about prompt engineering is a powerful way to save time, money, tokens and frustration.

I see a lot of people saying, "I tried it and it didn't work," but have they read the guides or just jumped right in?

For example, if you haven't read the claude code guide, you might have never setup mcp servers or taken advantage of slash commands.

Your CLAUDE.md might be trash, and maybe you're using @file wrong and blowing tokens or biasing your context wrong.

LLMs context windows can only scale so far before you start seeing diminishing returns, especially if the model or tools is compacting it.

Plan first, using planning modes to help you, decomposition the plan
Have the model keep track of important context externally (like in markdown files with checkboxes) so the model can recover when the context gets fucked up

https://www.promptingguide.ai/

https://www.anthropic.com/engineering/claude-code-best-practices

There are community guides that take this even further, but these are some starting references I found very valuable.

[–] onlyhalfminotaur@lemmy.world 18 points 13 hours ago (3 children)

So even more work than actual coding.

[–] expr@programming.dev 14 points 12 hours ago

Yup. It's insanity that this is not immediately obvious to every software engineer. I think we have some implicit tendency to assume we can make any tool work for us, no matter how bad.

Sometimes, the tool is simply bad and not worth using.

[–] Semi_Hemi_Demigod@lemmy.world 3 points 13 hours ago

Everyone is a senior engineer with an idiot intern now.

[–] TurdBurgler@sh.itjust.works 0 points 2 hours ago* (last edited 2 hours ago)

Early adopters will be rewarded by having better methodology by the time the tooling catches up.

Too busy trying to dunk on me than understand that you have some really helpful tools already.

[–] jacksilver@lemmy.world 5 points 9 hours ago (2 children)

While you're right that it's a new technology and not everyone is using it right, if it requires all of that setup and infrastructure to work then are we sure it provides a material benefit. Most projects never get that kind of attention at all, to require it for AI integration means that currently it may be more work than it's worth.

[–] TurdBurgler@sh.itjust.works 0 points 2 hours ago

This is why I say some people are going to lose their jobs to engineers using AI correctly, lol.

[–] onlinepersona@programming.dev -2 points 8 hours ago

"If I need to write boilerplate and learn a new skill, is it really worth it?"