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.

There's a formula I've bookmarked from someone to help you get better social capital. In order to increase your surface for social capital you need to expand your influence, therefore you need to increase your luck:

L (luck) = D (doing) x T (telling)

Basically, you need to be able to show you are able to do stuff (D) and with enough people seeing this by you sharing (T) through different channels, can open doors. I haven't been doing it as heavily but it has already given me incredible opportunities.

Best way to have social capital is an introduction into a space where money and power exist. Many spaces no matter what you do you will never be able to get in without an intro, and they have extremely few opportunities. Being college buddies with a member of an upper class is one of the only times they will ever socially mix. It is indeed like royalty in every way.

Being at Harvard gets you a lot relative to the population, being around the right clubs at Harvard gives you a lot relative to that. There is meritocracy within the range but nepotism can easily put people in the room. Work at a startup or two run by families of billionaires, and watch their career trajectory, and you will not have any doubt.

But what do you do if you can't stand the faintest smell of nepotism?

The sibling commenters are correct but I will add with the benefit of being an old guy that this ebbs and flows. GP said "I have never seen tech be less about engineering", and I agree.

But it can't get much less about engineering before rich people become poor in large numbers, and that will start the pendulum back the other way.

Rich people losing money that matters in large numbers is like a soft civil war, everything changes.

Struggle harder than you otherwise would, sadly.

Then you're fucked :)

i've been thinking about this as well. but having built a startup, i've learned that users don't care as long as they are given the value and most convenience. they don't really care much at security as much as we do. just look at openclaw? but maybe it's our job to make sure it is taken care of vs assuming the user cares and just make it look seamless.

users don’t care about security until it goes wrong. then they will be angry.

security is a hidden requirement.

my takeaway from this is that it should now be MANDATORY to have an LLM do a scan on the entire codebase prior to release or artifact creation. do NOT use third party plugins for this. it's so easy to create your own github action to digest the whole codebase and inspect third party code. it costs tokens yes but it's also cached and should be negligible spend for the security it brings.

Ironically, Trivy was the first known compromised package and its purpose is to scan container images to make sure they don't contain vulnerabilities. Kinda like the LLM in your scenario.

Not sure that Trivy was doing that itself but zizmor is probably better than starting with an LLM :

https://github.com/zizmorcore/zizmor