the problem, ironically, is that hucksters were selling other oils as "snake oil" when they didn't have the same omega 3s. the bad reputation was due to fake snake oil.
I feel like similar to the chinese, indian home cooking and indian restaurant cooking are very different; I can try my hand at a lot of restaurant style recipes at home but it's not what I usually cook or what I grew up eating at home.
if growing up in dubai was any indication, what happens (at least for the next little while) is you get a steady stream of desperately poor people who work until they wreck their health and then get replaced by the next desperate person.
I am guessing the people most disappointed with AI in the long run are the ones wanting some sort of arbitrage where they can generate products with low effort and then expect people to pay for access to them based on a paradigm where creating software at all required a lot of effort.
not intending to slam you personally, but the fact that you finished your projects and then lost interest in them is very indicative of projects done for the sake of generating something with AI just because you could.
I think the people who succeed will be the ones who are willing to develop a project with high effort, and then use the LLM to help with some of that effort. not just because in a world where everyone has access to the same AI code generators the effort is the value add, but because a good product genuinely does require a lot of human input and supervision being l beyond simply churning out code.
I agree. In my case none of the projects was something paywalled and we're developed with sole intent to learn. Some we're data heavy which we're most of the work and I didn't had any experience before.
What I meant is the "aftercare" when product is publicized. Like promoting it in some way, maybe using a social media to promote it properly? No idea. This is another thing I know absolutely nothing about, so It would be wise to learn it. I usually just let them hang to be indexed by google and chatbots which drives some traffic, but it's basically just running app not a product.
What I meant is, that OP spend quite a lot of money on that so I was curious if he have any plan. :)
i've been running claude in what the blog calls phase 0 for the last 6-7 months. i'm perfectly happy with it, my development velocity has increased while i still have a good grasp of the entire app, and i've actually been making decent progress with web development for a personal project, which is something i've bounced off several times in the past. also i do not get stuck as often on stuff like "how do i get django to statically serve up a js bundle with relative imports" which is more about knowing specific APIs of specific frameworks than any feature of my code or architecture.
i would not want to go down the "take myself out of the loop" path because yes, i do have to micromanage the claude session, often course-correcting every commit and then doing large scale refactoring every so often. but i'm perfectly happy doing that - i see claude as more of a tool than a coder i can hand work off to.
i just ran into a concrete example of why i would not want to run a tree of unsupervised agents churning out code. i have a project that generates large but repetitive .docx documents. i asked claude to add some graphics to it, it did a very good job of figuring out the xml graphics elements, locating where in the document structure it could insert them, and even printing to pdf and checking visually to get them perfectly lined up with the text. it took some 5 minutes, i would likely have spent an hour doing all that from scratch including several trips to google.
then i looked at the code and asked it to benchmark, hinting that it looked like it was doing a lot in the inner loop. and sure enough, adding a few simple graphics to every page more doubled the time it took to generate the largest size of document (~1s -> ~2.2s for ~400 pages). without any more prompting claude figured out that it had an accidentally-quadratic loop, and fixed that.
i then had to tell it "look, we are using a template to avoid regenerating boilerplate with every page. you can add a placeholder to the template and replace it with graphics using xml patching code you already wrote for another part of the doc generation". the final code was a lot cleaner and ran in ~1.2s, which claude (again unprompted, to its credit) did fine-grained benchmarking to prove was the unavoidable overhead of simply inserting all those large chunks of xml into the document.
i wouldn't even say it was a coincidence that i ran into this right after writing my comment about having to micromanage the LLM, because this sort of thing happens all the time. i can say that i had a much easier time doing this because i looked at the code generated in a single commit and could easily see that it smelt off. i would have not have wanted to do this at the end of 20 commits all building on each other.
it's the colour scheme that I remember most strongly. I still think "very prince of persia" when I see certain colour combinations, especially cream and purple.
the solution might be checklisting in lieu of time tracking - rather than note what you spend each moment on, define tasks and subtasks, and work on one set of subtasks at a time. the checklist helps maintain focus because if you think of something random you can note it down for later rather than jump straight into it.
AI has made this way worse - now the thinking is "well, the agent is doing all the work, why can't the engineers make sure it is running on all cylinders all the time, churning out useful code"
reply