westoque

> It absolutely is a harmless feature that you can ignore. There’s no reason not to have one

what i've learning developing and creating products over the years is that harmless features tend to be the ones that cause the most problems. for ex, now you have to add touchscreen code to the OS vs previously not having it at all. and this code or feature we will support for the rest of the lifetime of that product.

from the project https://github.com/antirez/ds4 it was said that:

> It must be more a working template for the biggest use cases, without trying to cover every possible setup.

this is such a great quote about building software in the AI age. given that everyone has a different use case, the best way for open source software to be built is to build it for the general use case and specialization could be done afterwards.

funny anecdote. i was traveling in europe around 2011 and i was staying at a hostel. the hostel had a session where all the travelers go in a circle and introduce themselves. i mentioned i was from "america" and this south american lady got triggered and said "you know there's also SOUTH america right?" and after that i never used the word america anymore and just say i'm from the USA.

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.

> 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.

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.

with agent loops, the cost of exposing bugs should be cheap now. every pen tester should be using agent loops and on the flip side, an agent could easily see this issue once filed and a fix immediately done. it's incredible how cheap code is now.

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.

> 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.

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.

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.

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.

> The problem for me is that the development practices of the people that are working on it are suboptimal at best; they're constantly releasing at an extremely high cadence, where they don't even spend the time to test or fix things (or even build a proper list of changes for each release), and they add, remove, refine, change, fix, and break features constantly at that accelerated pace.

this is what i notice with openclaw as well. there have been releases where they break production features. unfortunately this is what happens when code becomes a commidity, everyone thinks that shipping fast is the moat but at the expense of suboptimality since they know a fix can be implemented quickly on the next release.

one thing it did massively for me was save me time from questions like should i go with X or Y option questions. before i used to just think longer about tradeoffs but with AI it became a lot faster. no more procrastination due to decision fatigue.

> I simply booted up a VM with an H100, ssh’d into it with Cursor, and prompted the agent to set up an inference server that I could ping from my web generation app. What used to take hours or days of painful, slow debugging now takes literally minutes.

an awesome takeaway from this is that self-hosted models are the future! can't wait for hardware to catch up and we can do much more experiments on our laptops!

i really think this is part of the pitch deck for bun's funding. that a bigger company would acquire it for the technology. the only reason an AI company or any company for that matter would acquire it would be to:

1. acquire talent.

2. control the future roadmap of bun.

i think it's really 1.

> Current AI image models can't understand grid-based pixel art.

sounds like a good use case to fix this problem from the model layer. an image gen model that is trained to make pixel perfect art.

i like how claude code currently does it. it asks permission for every command to be ran before doing so. now having a local model with this behavior will certainly mitigate this behavior. imagine before the AI hits the webhook.site it asks you

AI will visit site webhook.site..... allow this command? 1. Yes 2. No

a concern i have is that it's only a matter of time before a similar attack is done to electron based apps (which also have packages installed using npm). probably worse because it's installed in your computer and can potentially get any information especially given admin privileges.

Recently launched an AI cafe ordering app https://www.hellocafe.ai using chat and voice.

We wanted to make concept for an app using all local models for chat (llama 3.1 8B) and voice (whisper). Deployed using kubernetes and easily scalable not to mention fully open source!

Refreshing that it's built using the vue framework vs the typical react.

> They're getting my $200 a month and it's easily the best money I spend

Can you explain? I don't see how $200 makes that much difference than what I get from paying $20/month with OpenAI? What's the use case?

Came here to say this. What makes a great general purpose language is not only in the programming part but also in transportability. I think Go takes the cake here. If only Elixir apps could be compiled and transported as a binary to similar systems and it works, then it would make it a great general purpose language. Until then, it's really only a good client/server language as it was intended to be.