The insane billion dollar companies ship straight to production because they have PMF so anything and everything gets signal.

The same happened with Facebook and Google. And it was always cautionary advice to mimic these giants. It's a bad idea for all the rest of us.

Instead, reads like you're blaming the victim. Shoulda worked harder in school!

I'm a millennial. It occurred to just the other day, the language they use, they say "dough" a lot. They need dough. Where's the dough. Any criminal is always involved with gambling and gangs and they need dough! And the normal working people storylines are pinned to their lack-of-dough situations.

I remember the internet very fondly too. There's always an age of innocence but it just takes time to realize everyone just really needs and wants dough. And that's what happens.

It's no more conscious than running that cron job to send you today's weather. That's as far as I understand what this link is. The agent is posting blog updates and such. Because it was told to. It has no will. LLM generative output is incredible. It's also not conscious.

but i could be wrong.

LLMs are objectively smarter than any one person so in some definition we've already created super-intelligence. The problem is they just sit there. They have all the answers already, if you think about it. Whenever we ask it something it gives us the answer, it's amazing, we can even say it can synthesize new information. We can agree with all the claims.

But what does it do with that super-intelligence? Nothing. It can't. it doesn't have will. Or interest. Curiosity? Biological imperative. Who knows.

So we create loops and introspection and set them free. Does giving AI a goal make the AI conscious? That's easily silly if you ask me.

(I'm trying really hard not to make this philosophy. I really like the philosophy aspect, but this is my 30 second answer to the question)

I'm not blind, I have Claude pro (not max) and Cursor subscription. But I'm really hesitant to go balls to the wall on the most powerful models because it isn't sustainable; I don't want it to be. So how much can I get from the older models, the smaller, cheaper ones that will hopefully inevitably be commoditized. I think the harness improvements are making headway. I continue to think Cursor Composer 2 is more than adequate.

Then again if one believes it's a race to the singularity, then that's another story. I don't.

Admittedly, with Opus 4.6+, GPT 5.5 I just haven't used them much and as I gain more experience I can see what the hype is all about. But to me, the answer isn't $200 max plan, it's bifurcating the work. Call me a spendthrift!

I think it means something like we're trapped in the constraints of the medium. Tweets say more about the environment of twitter than whatever message happened to be sent.

but i think im off on that, ill look this person up and find out!

Pretty sure she founded or runs skims? She's Armenian, daughter of a famous lawyer in LA. Kanye. Sex tape. Early with the reality tv. I too did not seek out any of this knowledge!

Most just be a generational thing. Sweeney is still baking. She's actress from euphoria of which i didn't watch. That's about as much as i know. and the jeans ad controversy.

The signals are working as intended. More people will know Kim K than Sweeney because Kim K is more popular and has had more time to be more popular.

why am i talking about kim k on hn lol

But the more you read the article the more the point is lost. The prescriptions given aren't ambient?

    CLI: a good command-line interface makes it easy for an agent loop to interact with your system and saves tokens.
    Specs: Declarative configs, schemas, manifests. Artifacts that state the desired outcome, not the steps.
    Reconciliation loops: you declare the target state, let the system continuously converge toward it. Detect if something drifts.

The gripe seems to be specifically with being able to chat with the AI. Yes, ideally the AI just knows to do stuff. But the chat interface is also the reason every Bob and Sarah has chatGPT in their pocket. It's also just growing pains.

Quote of the week for me. well said.

~15 years ago I fumbled around with web programming basically because I never learned how to use excel in school. Nerded out with css, html, forms, then php and mysql to script together an unbelievably worse version of what a spreadsheet could do, but it was incredible that I could build something entirely made for my idea. And with the power to improve it.

Thank you for writing and sharing your story, it's motivating and comforting even. Good luck!

Now for the criticism: back in the day mint.com was mind-blowing. It's what you always thought you'd wanted. The graphs were interactive and pretty and you really loved seeing them go up. Not so much down. I was so attached to the gamified aspects, much like step counters. They reinforce habits.

My mint journey ended with roughly 5 years or so of data, once they sold to Intuit, didn't like the ads and willingly syncing all my data to mega-corp. Much like Duolingo, it felt good at the time, but I don't know that it did anything for me at all.

Tracking is a double-edged sword: it really does build better habits. It's better to track weight every day for example so you better understand that fluctuations are mostly noise. The daily tracking stuff is entirely useful to get the need to track daily out of your system.

TLDR: checking my net-worth daily sounds like something I should coach myself out from. Ironically that probably takes tools, but the end goal is to not need them.

and it's really slow. I didn't end up waiting. Not a slight to the creators, let them create. It's just really freaking slow I didn't wait.

Opus, I watch my allotment creep up every turn…