Well, I rely on it a lot, but not in the IDE, I copy/paste my code and prompts between the ide and LLM. By now I have a library of prompts in each project I can tweak that I can just reuse. It makes me 25% up to 50% faster. Does this mean every project t is done in 50/75% of the time? No, the actual completion time is maybe 10% faster, but i do get a lot more time to spend on thinking about the overall design instead of writing boilerplate and reading reference documents.
Why no youtube videos thought? Well, most dev you tubers are actual devs that cultivate an image of "I'm faster than LLM, I never re-read library references, I memorise them on first read" and do on. If they then show you a video how they forgot the syntax for this or that maven plugin config and how LLM fills it in 10s instead of a 5min Google search that makes them look less capable on their own. Why would they do that?
Why don’t you read reference documents? The thing with bite-sized information is that is never gives you a coherent global view of the space. It’s like exploring a territory by crawling instead of using a map.
Why no youtube videos thought? Well, most dev you tubers are actual devs that cultivate an image of "I'm faster than LLM, I never re-read library references, I memorise them on first read" and do on. If they then show you a video how they forgot the syntax for this or that maven plugin config and how LLM fills it in 10s instead of a 5min Google search that makes them look less capable on their own. Why would they do that?