Another frustrating thing that has emerged from this is where managers “vibe code” half-baked ideas for a couple of hours and then hand it off as if they’ve meaningfully contributed to the implementation. Suddenly you’re expected to reverse engineer incoherent prompts, inconsistent code, and random abstractions that nobody fully understands.
In their mind they’ve already done the “architectural heavy lifting” and accelerated the team.
More often than not it just adds cognitive overhead where you spend more time deciphering and cleaning up garbage than actually building the thing properly from scratch.
While this is a legitimate set of rules to follow for maintaining code sanity and a solid mental model of how a codebase may grow, it’s always challenging to stick to them in a workplace where expectations around delivery speed have changed drastically with the onset of AI. The sweet spot lies in striking a balance between staying connected to the codebase and not becoming a limiting factor for the team at the same time.
It gives you clean text summaries of YouTube videos. There are obviously other tools that do this, but I wanted something that is aligned with actual principles of learning and retention, not just quick TLDRs.
Also added a feature called Related Videos. It extracts the key themes from a video and recommends the top 3 related videos, essentially creating a small “knowledge web” of sorts around the topic. Similar to youtube recommendations, but you don't watch you click and read.
You can do YouTube search directly inside the product. When you click a video, it generates a summary. So you’re still browsing YouTube, but click turns a video into something you can actually consume. Personally found it better way to consume youtube, quicker for me to get through the content I want to consume than have those 10+ Youtube tabs sitting in my browser forever.
There’s also a public library feature I added where you can make your summary public. It’s kind of fun to see what other people are learning.
Still early, but iterating on it, scratching my own itch.
Searching for what to solve becomes far more important than how to solve it. Which niche you serve, how underserved the problem is, how quickly you build a solution, and how fast you iterate based on user feedback become the real differentiators. As a problem gains popularity, competitors will enter at an increasing pace, and the product’s price will be competed down to the bare minimum. At that point, the only real advantage for a builder is to be a serial builder for deep niches, spotting them faster than others and delivering quality product to users before anyone else.
In their mind they’ve already done the “architectural heavy lifting” and accelerated the team. More often than not it just adds cognitive overhead where you spend more time deciphering and cleaning up garbage than actually building the thing properly from scratch.