not a fan of README's where there's no clear way to run the program, like a getting started or how to build. i think this is the opposite of a docu-monster where AI documents everything, but clearly more documentation is better than lack of.

I came to say the same thing. Zero info about how I would use this once it’s cloned.

It’s a library and there are usage examples.

> but clearly more documentation is better than lack of

I tend to disagree. This makes it very high signal. So far my agent has been successful at navigating the repo.

> But like every habit, the only thing you have to do is to keep at it. And if you pay enough attention to it, something will click in your brain.

a bad habit i noticed after taking hiatus of focused work was me jumping into different windows and tabs and just mindlessly consuming content without finishing them. after noticing this pattern, i decided i will focus on one task at a time and finishing it, like reading the OPs article. it did wonders for me and i noticed i'm now even more focused that ever. the lesson is indeed being aware first, and then practicing the habit.

I have this same problem. I am not sure if medication will help but I really don't want to go there. My brain is a scattered mess. Even now, I am doing 3 other things at the same time. Is it a matter of "getting good" and just focus? I just don't think there's a secret technique to this.

I think a lot of people struggle with this. Technical work already promoted this kind of behavior since it rewards a very heavy "just in time" lookup style for finding information (we've all had hundreds of chrome tabs open at work before, right?)

And on top of that work chat

And now agents, which are basically all designed for you to spin up several different conversation threads and hop between them constantly while the agent works.

It's no wonder people can't focus. Both work and leisure are basically designed to split up your attention into microscopic fragments.

I see the same pattern with people on their phones. Opening up an app, immediately switching to the next app, repeat.

ok. a similar idea, you should put a camera outside your door and do the same for passing dogs.

my idea of de-brainrot is by going to destinations where everything is new and experiencing everything there physically & mentally. either going to a new city or drive to a new place. i'm not sure if it's anecdotal but there's a feeling of astonishment when experiencing a new place. i find that when you go back you have this new perspective and you feel refreshed.

I have experienced a similar feeling. Often I will dream of the newly "mapped" area once I arrive home (with cartoonish/dreamlike elements that are far from perfect). After I awake from this dream I feel likewise refreshed.

this is exactly my setup! the ipad pro 11 m5 cellular is such an amazing device especially with the 5G. only downside is obv the iPadOS, it's still very limiting and shortcuts and power tools (like easily prefilling passwords) are non-existent. for passwords, you still have to manually click the pre-fill and/or enable full keyboard to be able to tab into it but still annoying.

i can see the resemblence and that's what separates the more marketable app.

i just did an AI hackathon and 90% of the submissions were written in TypeScript and Next.js which is mostly due to the training data. AI is skewed to use these tools by default vs the best for the job.

I don't think random blogs should be ruled out. Just because a blog is random doesn't mean its untrue.

The reputation of the writer matters a lot. Recent models seem to be pretty good at evaluating author credibility as well.

What's dangerous is treating information from an anonymous author as factual. You gotta check that in other ways.

It should not be seen a credible source though.

It can be, but that's hard to correctly judge on at scale.

> Comparing agentic Qwen3.6 35b to Claude Opus is like a junior with knowledge across the board, that you really need to guide, versus a senior that thinks with you on architecture.

that's why i use the frontier models because its a senior co-worker vs a junior. if you use the junior for the sake of privacy i think you're missing out on the best insights for a specific task.

The dilemma I am facing is cost.

Consumer-grade subscriptions of the frontier models give you superb capabilities per dollar, them being heavily subsidized. But if you're working in an enterprise setting, that won't work. You need to upgrade, and that gets significantly more expensive.

Furthermore, basing the SDLC on leveraging the bargain subscriptions risks falling apart in the future, both from a cost perspective as well as the question of availability (e.g. Mythos).

So from a strategic perspective, going local on the LLM and still achieving great results with the right approach is very relevant.

Or you can get the best of both worlds--use frontier models to build a spec/plan, and use cheap models (open source or not) for implementation. Your max or team plan can go a lot further this way without giving up much for quality. Play with something like Superpowers to make this really approachable.

Best insights can be over rated due to bandwith limitation of the brain. Even if Einstein is sitting next to you the whole day and helping out Theory of Bounded Rationality applies.