Lately I have had the cursed vision as I'm building a new IoT product. I have to learn _so_ much, so I have stopped using claude code. I find directly altering my code too hands off.
Instead I still use claude in the browser mainly for high level thinking/architecture > generating small chunks of code > copying pasta-ing it over. I always make sure I'm reading said library/code docs as well and asking claude to clarify anything I'm unsure of. This is akin to when I started development using stackoverflow just 10x productive. And I still feel like I'm learning along the way.
I wouldn't call that cursed but useful tooling usage. Had the same scenario where I wanted to work on a tool for a project written in Go, of which I know next to nothing. Claude code was able to spit out 100's line of code that worked and I (almost) understood and could explain what was happening where and why, but I had no chance of debugging or extending it on my own.
I've limited myself to only use Claude's webchat to do almost exactly as you've mentioned except creating snippets, it can only explain or debug code I enter. I prompt it to link relevant sources for solutions I seek. Plus it assists me subdivide, prioritise and plan my project in chunks so I don't get lost.
It has saved me a lot of time this way while still enjoying working on a project
Yeah it actually is beautiful, because we get the brainstorming ideas so that ,sometimes we lack the experience in coding to get that idea to be converted into a powerful working application ,we need the artificial intelligence so that ,we can always enjoy the process , only if we are loving the work we are doing ,I mean there is a lot of difference between blind pasting and completing a work ,just my opinion of what I have been through
Interesting how you write the code first then put it into claude. What's the reason there?
I guess that is where I find the most benefit is not writing out the syntax, even though I could I just can't be bothered. I often start with the snippet then refactor to the style of code I like. For code I don't know that well like c++ I like to get a snippet so I can then research into those functions that is used and go from there.
Mostly because I learn the best by doing, reiterating and then expanding, especially with programming. Essentialy, building a form of context or mindmap if you will.
When I was testing Typescript/React I followed the docs and some guides and got thrown in the deep end, I could follow and understand the steps but not reproduce or adapt them because the (or my) scope was limited, also, libraries; so many libraries used..
By starting with a HelloWorld and expanding it step by step, going back and forth. Using forums/blogs to see available functions or similar oss projects for what I wanted to do, then use the docs to read about the used functions.
Kagi already helped save me a lot of time by reducing spam posts and using language shebangs etc. With Claude I either give a snippet that I cannot translate or am stuck on, like you do, or I'll prompt something like: 'describe steps used to get from input=.. to output=.. in go, this/that needs to be done/transformed, do not output actual code'.
I guess the main thing is that I want to be engaged in my personal/hobby projects and think about the problem and solution and not just copy/paste because that takes the fun away (in case of work, if it makes me more productive I'll take it. Just need to remember I'm the one who is responsible). It's like buying a pre-assembled puzzle.
I'm almost like you, I just download what I want to watch. But instead of going through network files - I have Plex Media Server on my M1 Macbook Air. Plex looks at the downloads folder, indexes it into a nice viewing experience that I use Plex app on the TV to connect to my local Plex server. It's a very seamless experience.
The Will of the Many. An epic high fantasy adventure. I’m just about to finish the second book in the series - The Strength of the Few. I haven’t gasped this many times reading a book in while.
Same here! I’m on the final 200 pages. It’s going to painful waiting so long for the third in the series. I went straight from book 1 to 2 with no wait thankfully.
My parents literally just gave my daughter the alphabet puzzle for Christmas that was linked in the article as a terrible clean up vs play-time. I might send them this link!
These are fantastic! I've done similar and seen some positive outcomes at work. As the one usually sending meetings - I have been leaning heavily on asynchronous first (teams chat) then if needed we hop into a focused meeting with a clear agenda. It's been liberating to see the reactions that other people like this too instead of another meeting. More often than not we never needed the meeting.
If a master craftsperson records a video in their workshop demonstrating their craft and talking about their craft, you are observing mastery. This isn't some wild theory, this is a cold hard fact. Which leads us to the question, what the hell are you talking about?
You seem upset. I am not sure why. There are so many potential problems in between a YouTube search and actual success that I won't expand further. You'd learn more in the shop.
You've moved the posts from "watching youtube" to "searching youtube", then added something about my emotional state.
Doesn't surprise me you don't want to expand further, since you have nothing to expand. When the craftsperson makes a tutorial video, complete with close-up shots, and organised edited presentation, with more than one take on their side, it can be superior to going to their workshop. Both can be useful, but your argument that "youtube" is disqualified from offering value to those wanting to observe mastery, is a broken argument. Instead of running away, why not admit your error?
Pretty solid - I'll add this to my list that I refer to for writing. I often use the Australian Style Manual [0] and Divio Documentation System [1] as a foundation to technical writing and also user documentation.
I disagree with this take. I work very closely with my UX lead and we always do lo-fi in Miro/Figjam before hi-fi designs in Figma. This gives us flexibility of expression to quickly mock things up loosely before going into the final design. Auto-layout, components is a huge win for designers. We were on another design product called UXPin which didn't have this sophistication and it was an absolute drag.
Instead I still use claude in the browser mainly for high level thinking/architecture > generating small chunks of code > copying pasta-ing it over. I always make sure I'm reading said library/code docs as well and asking claude to clarify anything I'm unsure of. This is akin to when I started development using stackoverflow just 10x productive. And I still feel like I'm learning along the way.
reply