The person they are responding with dictated an authoritative framing that isn’t true.
I know people have emotional responses to this, but if you think people aren’t effectively using agents to ship code in lots of domains, including existing legacy code bases, you are incorrect.
Do we know exactly how to do that well, of course not, we still fruitlessly argue about how humans should write software. But there is a growing body of techniques on how to do agent first development, and a lot of those techniques are naturally converging because they work.
The views I see often shared here are typical of those in the trenches of the tech industry: conservative.
I get it; I do. It's rapidly challenging the paradigm that we've setup over the years in a way that it's incredibly jarring, but this is going to be our new reality or you're going to be left behind in MOST industries; highly regulated industries are a different beast.
So; instead of just out-of-hand dismissing this, figure out the best ways to integrate agents into your and your teams'/companies' workstreams. It will accelerate the work and change your role from what it is today to something different; something that takes time and experience to work with.
> I get it; I do. It's rapidly challenging the paradigm that we've setup over the years in a way that it's incredibly jarring,
But it's not the argument. The argument is that these tools provide lower-quality output and checking this output often takes more time than doing this work oneself. It's not that "we're conservative and afraid of changes", heck, you're talking to a crowd that used to celebrate a new JS framework every week!
There is a push to accept lower quality and to treat it as a new normal, and people who appreciate high-quality architecture and code express their concern.
"Find any inconsistencies that should be addressed in this codebase according to DRY and related best practices"
This doesn't hurt to try and will give valuable and detailed feedback much more quickly than even an experienced developer seeing the project for the first time.
These kinds of instructions are the main added value of LLMs and I use them every day. Even though 30%-60% the output is wrong/irrelevant, the rest is helpful enough. After the human reviews it, the overall quality of the codebase increases, not decreases. This is on the opposite end of the spectrum when compared to agentic coding, though.
I've been using LLMs to augment development since early December 2023. I've expanded the scope and complexity of the changes made since then as the models grew. Before beads existed, I used a folder of markdown files for externalized memory.
Just because you were late to the party doesn't mean all of us were.
> Just because you were late to the party doesn't mean all of us were.
It wasn't a party I liked back in 2023. I'm just repeating the same stuff I see said over and over again here, but there has been a step change with Opus 4.5.
You can still it in action now because the other models are still where Opus was at a while ago. I recently needed to make small change to script I was using. It is a tiny (50 line) script written with the help of AI's ages ago, but was subtly wrong in so many ways. It's now become clear neither the AI's (I used several and cross checked) nor myself had a clue about what we were dealing with. The current "seems to work" version was created after much blood caused by misunderstandings was spilt, exposing bugs that had to be fixed.
I asked Claude 4.6 to fix yet another misunderstanding, and the result was a patch changing the minimum number of lines to get the job done. Just reviewing such a surgical modification was far easier than doing it myself.
I gave exactly the same prompt to Gemini. The result was a wholesale rearrangement of the code. Maybe it was good, but the effort to verify that was far lager than just doing it myself. It was a very 2023 experience.
The usual 2023 experience for me was ask an AI write some greenfield code, and get a result that looked like someone had changed variable names in something they found on the web after a brief search for code that looked like it might do a similar job. If you got lucky, it might have found something that was indeed very similar, but in my case that was rare. Asking it to modify code unlike something it had seen before was like asking someone to poke your eyes with a stick.
As I said, some of the organisers of this style of party seem have gotten their act together, so now it is well worth joining their parties. But this is a newish development.
If you hired a person six months ago and in that time they'd produced a ton of useful code for your product, wouldn't you say with authoritative framing that their hiring was a good decision?
It would, but I haven’t seen that. What I’ve seen is a lot of people setting up cool agent workflows which feel very productive, but aren’t producing coherent work.
This may be a result of me using tools poorly, or more likely evaluating merits which matter less than I think. But I don’t think we can see that yet as people just invented these agent workflows and we haven’t seen it yet.
Note that the situation was not that different before LLMs. I’ve seen PMs with all the tickets setup, engineers making PRs with reviews, etc and not making progress on the product. The process can be emulated without substantive work.
If there is one thing I have seen is that there is a subset of intellectual people will still be adverse to learning new tools, hang to ideological beliefs (I feel this though, watching programming as you know it die in a way, kinda makes you not want to follow it) and would prefer to just be lazy and not properly dogfood and learn their new tooling.
I'm seeing amazing result to with agents, when provided an well formed knowledge base and directed through each piece of work like its a sprint. Review and iron out scope requirements, api surface/contract, have agents create multi phase implementation plans and technical specifications in a share dev directory and to make high quality changes logs, document future consideration and any bugs/issues found that can be deferred. Every phase is addressed with a human code review along with gemini who is great at catching drift from spec and bugs in less obvious places.
While I'm sure an enterprise code base could still be an issue and would require even more direction (and opus I wont let touch java, it codes like an enterprise java greybeard who loves to create an interface/factory for everything), I think that's still just a tooling issues.
I'm not of the super pro AI camp, but having followed its development and used it throughout. For the first time I am actual amazed and bothered, and convinced if people dont embrace these tools, they will be left behind. No they dont 10-100x a jr dev, but if someone has proper domain knowledge to direct the agent, performs dual research with it to iron things out with the human actually understanding the problem space, 2-5x seems quite reasonable currently if driven by a capable developer. But this just move the work to review and documentation maintenance/crafting. Which has its own fatigue and is less rewarding for a programmers mind who loves to solve challenges and gets dopamine from it .
But given how man people are adverse...I dont think anyone who embraces it is going to have job security issues and be replaced, but here are many capable engineers who might due to their own reservations. I'm amazed by how many intelligent and capable people try llms/agents like a political straw man, there is no reasoning with them. They say vibe coding sucks (it does for anything more than a small throw away that wont be maintained), yet their examples for agents/llm not working is it can't just take a prompt and produce the best code ever and automatically and manifest the knowledge needed to work on their codebase. You still need to put in effort and learn to actually perform the engineering with the tools, but if it doesnt take a paragraph with no AGENTS.md and turn it into a feature or bug fix they are not good to them. Yeah they will get distracted and fuck up, just like if you throw 9/10 developers in the same situation and told them to get to work with no knowledge of the code base or domain and have their pr in by noon.
Garry is a good person and smearing people over their church is a disgusting thing to do.
I am now going to sit here and listen to this talk because I guarantee it's not saying what you think it's saying. And I don't want to listen to it. It's not a topic that interests me. But I guarantee you are completely distorting what was stated in that topic for maximum effect, entirely motivated by left-wing politics.
I imagine you are not done listening to them yet as the total over 8 hrs. But my research is showing that OPs are largely correct. Theil gave several talks to his church where he did in fact say these things.
In your post you state you are ‘not sure’, but also that that the poster is ‘wrong’.
> My thesis is that in the 17th, 18th century, the antichrist would have been a Dr Strangelove, a scientist who did all this sort of evil crazy science. In the 21st century, the antichrist is a luddite who wants to stop all science. It’s someone like Greta or Eliezer.
Sure, he eventually goes on to say stuff like..
> One of the ways these things always get reported is, I denounce Greta as an antichrist. And I want to be very clear: Greta is, I mean she’s maybe sort of a type or a shadow of an antichrist of a sort that would be tempting. But I don’t want to flatter her too much. So with Greta, you shouldn’t take her as the antichrist for sure. With AOC, you can choose whether or not you want to believe this disclaimer that I just gave
But I don’t think this is the win that you might think it is. The dude is a loon.
You are wrong. Thiel's talks are as insane as we're saying. Also, it's not "disgusting" to tar people for belonging to a known toxic community of lunatics. It's completely rational. Cut the fake outrage. Idiotic religious beliefs don't have the same sacred value to most of us as they do to you.
Going by your comment history any criticism of Thiel and the administration is just left wing politics, but hard to hear you over the sound of drowning yourself with kool-aid.
Weird that you seem to support this administration that Thiel is very much associated with but find it offensive when there's a very clear association between Thiel and Garry. He's just going to this specific church to pray or whatever? Paying no mind to the anti-christ talk happening next door. I do hope this is the last breaths of religion in the western world, it needs to die.
I've been on HN for well over 10 years. I literally volunteered for Obama's 2008 and 2012 campaigns, and my comments in that time period clearly show my politics. I taught free web scraping workshops at the Center for American Progress to journalists back then. None of my policy preferences have changed. What's changed is the frothing at the mouth radicalism and moralizing of the team I used to support.
I'm not religious, and hate religious radicals, but ideologues act identically, just with secular idols. I didn't see that until I watched what the leftist ideologies did to the quality of life in two places I used to live in:
SF and Boulder.
I'm a 2012 Democrat, which makes me a fascist to a 2026 Democrat.
You have made a false claim. What is your evidence that I am religious, let alone a religious radical?
I mean, if we're going to make accusations based on perceived political tribal allegiances, I can say to you with equal certainty that you're a neo-Marxist.
Of course I don't know that. And you don't know anything about me.
Reminder that HN is SV centered and therefore everyone and everything is oriented around tribal group think.
Meta was funded by Thiel, yet most of the people in this thread use their products.
The CCP has technology that dwarfs Palantir, but a ton of people in this thread use TikTok, because they don't recognize fascism unless it's perpetrated by somebody that looks like the Nazis they see in movies.
I grew up around brainwashed religious zealots. I hated it. Everything was this moralistic condemnation and guilt by association game, played by people who had absolutely no sense of perspective and had zero interactions outside of there group think circles. Constantly condemning people they don't know and have never met and don't understand.
I've been on HN for 13 years now. It looks more and more like that every day.
This comment will be down voted without any substantive critique other than "I guess you're a fascist too."
Meanwhile, Discord will not have the slightest tiny drop in user numbers, because nobody outside of this moralistic circle jerk cares.
> Reminder that HN is SV centered and therefore everyone and everything is oriented around tribal group think.
Don't such absolute statements (everyone, everything) remind you of religion as well?
> Meta was funded by Thiel, yet most of the people in this thread use their products.
I imagine it might be as true as:
- most people in this thread also using Discord, despite criticizing it and
- most people using Meta criticize its products.
That is, You can use something and criticize it, and it probably happens both with Discord and e.g. Facebook.
> The CCP[…]
I'm happy to see in the political threads there's very often in the very least a significant presence of critique against China and maybe even overwhelming the defenders of the regime.
> I grew up around brainwashed religious zealots. […] moralistic condemnation […] [HN] looks more and more like that every day.
I think it's good religious zealots don't have the monopoly on moralistic condemnation. Just because A is bad, and B has feature x just like A, doesn't mean the feature x is bad.
> Meanwhile, Discord will not have the slightest tiny drop in user numbers, because nobody outside of this moralistic circle jerk cares.
Discord is not going to delete users, and few people care to request their account to be deleted. If Discord asked me to provide ID, I'd probably at least try to resist by not using it and maybe eventually succumb by providing a fake ID - but as far as I know, Discord will just set my account to a teenager mode, so instead of speaking about a drop in user numbers, we should speak about a drop of activity in adult interactions (or interactions/activity in general) on Discord.
Spot on. I wish this site was never associated with the term hacker because under the thin veneer of people doing cool things with tech, there is today nothing more authoritarian, narrow minded, overconfident and establishment than SV tech culture.
> Constantly condemning people they don't know and have never met and don't understand.
> therefore everyone and everything is oriented around tribal group think
You can be more convincing if you don't group everyone into one bucket and throw insults at it.
A reader can pull your claims out - meta bad, thiel bad, ccp bad, sheeple bad - but there isn't anything substantive there (WHY are these bad; it's all ad hominem so far) and we have to sift through a bunch of insults in order to do it ( 1. Tribal group thinkers. 2. Can't recognize fascism. 3. Looking like religious zealots blindly condemning people we don't know. 4. Going to downvote without thinking or participating.)
Your comment looks a LOT like insult #3 up there, with some whining thrown in on top.
If you want a substantive conversation or debate about the different facets of data privacy then lay the groundwork with some good faith place to start. If you instead just post mini screeds pre-insulting everyone then lamenting that nobody engages then nothing is going to change for you.
I just wish people would remember how awful and unprofessional and lazy most "journalists" are in 2026.
It's a slop job now.
Ars Technica, a supposedly reputable institution, has no editorial review. No checks. Just a lazy slop cannon journalist prompting an LLM to research and write articles for her.
Ask yourself if you think it's much different at other publications.
I work with the journalists at a local (state-wide) public media organization. It's night and day different from what is described at ars. These are people who are paid a third (or less) of what a sales engineer at meta makes. We have editorial review and ban LLMs for any editorial work except maybe alt-text if I can convince them to use it. They're over-worked, underpaid, and doing what very few people here (including me) have the dedication to do. But hey, if people didn't hate journalists they wouldn't be doing their job.
The most active HNers are just extremely negative on AI. I understand the impulse (you spend years honing your craft, and then something comes along and automates major portions of it) but it's driven by emotion and ego-defense and those engaged in it simply don't recognize what's motivating them. Their ego-defense is actually self-fulfilling, because they don't even try to properly learn how to leverage LLMs for coding so they give it a huge task they want it to fail on, don't properly break it into tasks, and then say "i told you it sucks" when it fails to one shot it.
Even this response shows why the most active ones are outwardly negative on AI.
I use AI a ton, but there are just way too many grifters right now, and their favorite refrain is to dismiss any amount of negativity with "oh you're just mad/scared/jealous/etc. it replaces you".
But people who actually build things don't talk like that, grifters do. You ask them what they've built before and after the current LLM takeoff and it's crickets or slop. Like the Inglourious Basterds fingers meme.
There's no way that someone complaining about coding agents not being there yet, can't simultaneously be someone who'd look forward to a day they could just will things into existence because it's not actually about what AI might build for them: it's about "line will go up and I've attached myself to the line like a barnacle, so I must proselytize everyone into joining me in pushing the line ever higher up"
These people have no understanding of what's happening, but they invent one completely divorced from any reality other than the reality them and their ilk have projected into thin air via clout.
It looks like mental illness and hoarding Mac Minis and it's distasteful to people who know better, especially since their nonsense is so overwhelmingly loud and noisy and starts to drown out any actual signal.
Yeah, we wouldn't want someone who understands the most revolutionary technology in 100 years to be the technical advisor to the mayor of the largest city in the United States or anything. That would be silly.
Why do you assume she doesn't understand it? From her Wikipedia article:
"Gelobter enrolled in Brown University in 1987, eventually graduating in 2011 with a Bachelor of Science in Computer Science with a concentration in artificial intelligence and machine learning."
My wife worked in several daycares in her early 20s, including an extremely expensive "Bright Horizons" location in a very affluent area. Even premium daycares provide inferior care to infants and young toddlers versus parental/family care. The economics of a business being in charge of your child demand this. Something that shocked her was at this super expensive daycare she worked at, the infants were basically given the bare minimum of attention while the older children consumed all of the time from the staff. The focus was on parental retention, so her job was to focus on changing the diapers of the infants to prevent diaper rash, and this took precedence over actually holding them and interacting with them. At no point is it remotely similar to how homo sapien mothers parent their OWN infants.
Daycare is to parenting as processed food is to nutrition. They are modern developments that prioritize economics over quality.
A study done in Canada (a "natural experiment", where a lottery determined eligibility for free daycare and allocated it at random) allowed researchers to track children who were enrolled in daycare versus children who were parented by their mothers, found that (adjusted for income) the infants who lost out on the lottery and were raised by their mothers in early childhood were healthier and better adjusted adults years later.
I am not arguing that parents should be deprived of paid parental leave until they are ready to go to preschool/daycare. I sm arguing that once the child is old enough to do that, it shouldn’t have to kneecap family finances to do so.
I agree. I think that paid parental leave and then later, paid daycare is an amazing investment of government resources. If we diverted a fraction of what we spend on retirees who had good jobs their whole lives and don't even need assistance to child care, society would benefit.
We spend far too much on former taxpayers instead of fostering and forming new taxpayers.
In Québec we have pretty extensive parental leave and we have heavily subsidized daycare (used to be 7$ a day per kid, now it's means-tested but you still get a hefty refund on your healthcare expenses come tax season).
When the program was put into place it paid for itself with the amount of mothers that entered the workforce.
I was raised by a single father, but thanks for derailing the conversation with your assumption that I'm a sexist because I didn't account for the edge case in parenting.
"Only if the mothers in aggregate truly believe that their children will have good lives, then will they have them."
Then please explain why birth rates throughout human history, when life was vastly more difficult and dangerous than it is now, were so much higher?
Nobody had to meet this bar you set before. Let's just be honest here. There were three recent developments, all of which were, by themselves, good things. But those three things, combined, created an unprecedented phenomenon.
The 3 things:
1.) The birth control pill decoupling sex from pregnancy.
2.) Women being granted autonomy and being allowed to join the workforce and leave marriages without suffering economic and social destruction
3.) Social support programs to create a poverty safety net funded by taxpayers instead of charity
No society on the planet ever had these things until the mid to late 20th century. And these things all contribute to radically reduced birth rates, in every single society that has implemented them together.
This take of "all you have to do is make the society encourage family formation" makes it sound like the three developments I listed are irrelevant, and that humans always just had this explicit menu of options that made family formation an optional pursuit, independent of a good life. That is simply not the case.
We need to be honest with ourselves about the uncharted territory we're in. It's not simple. Modern humans live in what would have been historically viewed as a Utopia. Our ancestors 5 generations back would have viewed our "jobs" as fake. They wouldn't even recognize what we do on a daily basis to earn food and shelter as labor of any kind. We have entire metropolises filled with people with soft hands who have literally never had to participate in their own survival from the perspective of harvesting food or cooking/heating fuel. Your comment just reeks of someone who is disconnected from the historical realities of 99.99999% of the humans who have ever lived.
You're comparing an average, but the demographics are different. If you compare, say, native-born-white to native-born-white, they fit those inputs much closer.
Total fertility is down because a smaller fraction of the population are immigrants from Mexico and Central/South America now and those immigrants have a higher birth rate. Their children regress to the mean.
The fertility rate has decreased significantly for US-born women of every race and ethnicity since the 1990s. I couldn't quickly find good stats on trend in birth control usage or labor force participation by race, ethnicity, or immigration status, but I'm skeptical that the trend is in the opposite direction for any particular demographic.
So I expect the claims in my previous comment still hold even for, e.g., native-born whites as a subgroup: flat-to-decreasing birth control usage, declining labor force participation, but still declining fertility rate. Obviously the magnitudes of those changes may be different at the subgroup level, but I don't see how the data is compatible with the claims of the comment I initially replied to.
> Modern humans live in what would have been historically viewed as a Utopia.
I think about this all the time, and how tragic (comedic?) it is that humanity finally created a Utopian age but most of its inhabitants are ignorant of that fact, and thus don't appreciate it, and instead genuinely believe they live in one of the worst times ever.
We are unhappy BECAUSE it's a utopia, and our brains evolved in a landscape that was ALWAYS trying to kill us. Like an immune system in an overly clean environment starts attacking inert things and creates allergies, our minds have created threats and focused on "relative" scarcity over actual scarcity. Instead of "How am I going to get enough calories to survive this week?" it's "Why does that guy get to be in a private jet and I have to fly coach?"
Yeah, you have a hard life as you type on a device powered by magic with a full belly and a roof over your head in a building that magically heats and cools itself. Compared to our ancestors, who alternated between fighting to not die of hypothermia or starvation or have their infants eaten by predators, you really have it hard dude. That bald guy on the TV has a really big yacht and you don't, and that means your life is a tragedy. I'm really sorry for the suffering you're enduring because you don't get to party all day, every day. Participating in your own survival is truly an imposition that nobody should ever have to bear.
Have you considered that rather than people being ignorant, not everyone lives this average experience, or that some portion of this increase in wellbeing creates collateral damage and those that experience it don't have the same rosy view?
This is also true. But once that happened, it was a sort of expectation and often necessity. People couldn't outsource as much hard work to machines, built by someone else far away from their farms
Yep. Birth control made it so women can choose how many times they get pregnant. Pregnancy is not exactly a walk in the park, so it’s no surprise it’s decreasing as birth control increases.
To override this, society needs to make having kids be “cool.” It’s that “simple,” but there’s no real way to coordinate that in society from the top down without being authoritarian.
So it’s a problem that can only be solved by individual change and convincing others one on one that it’s desirable. And people don’t like that.
I totally agree, and my argument with the original post was that the author made it sound so simple.
Has any society successfully done this yet?
Basically, the only prosperous first world groups I see with fertility rates above replacement rate are religious subcultures (like the Mormons, Evangelicals, and Modern Orthodox Jews in the US). I simply don't see any other examples of being able to pull this off.
Anything can become cool and desirable if enough people think it is.
The acceptance of LGBT was largely won this way. Same with women’s rights and environmentalism (although that one is still in the midst of fighting for success).
You just have to settle for a long road ahead before reaching any tipping point.
“A man who moves a mountain begins by carrying away small stones.”
> Then please explain why birth rates throughout human history, when life was vastly more difficult and dangerous than it is now, were so much higher?
Because having kids then was a way to increase quality of life. The kids could be put to work from a young age and help make money. Now, with so much modern tech doing physical tasks efficiently, a kid isn't going to add much value and instead is going to be a money sink.
The past is a foreign country. I do not believe "quality of life" in economic terms is a sufficient explanation. The simple Darwinian fact is that, if your culture did not value reproduction sufficiently, through whatever means, it would not have survived to the present. Remember, infanticide was widely practiced historically, and while not as convenient as birth control, provides a significant fraction of the same "benefit".
I do find it a bit ironic that "free child slave labor" is considered a better reason to have kids these days than, say, ancestor worship or nietzschean vitalism.
Yeah, as soon as you don't need children to help with your work, they don't make much sense in the capitalist individualistic society. That women still choose to do it, honestly... I see as a triumph of the human spirit
It's worth pointing out that pre-agricultural hunter gatherer societies also had low birth rates. They spaced their children out more, nursed longer, and didn't have as many kids overall.
Their population densities in pre-agricultural Europe were far lower than the agricultural societies that displaced them,
If, as another comment states, the countries with highest birth rates are Chad, Somalia, Congo, Afghanistan and Yemen, how does that square with your "Only if the mothers in aggregate truly believe" assertion?
> Your comment just reeks of someone who is disconnected from the historical realities of 99.99999% of the humans who have ever lived.
I was kinda nodding at points at your comment, or at least stroking my chin thinking, until the end. I had a feeling. You just came here to scold people.
> Then please explain why birth rates throughout human history, when life was vastly more difficult and dangerous than it is now, were so much higher?
> The birth control pill decoupling sex from pregnancy.
Boom. Done. You had the answer already and just didn't reconcile your own thoughts.
You really need to interpret the comment you're replying to in the context of here and now, not 100 years ago before people had a choice about whether to get pregnant from sex. Doing otherwise is misleading.
Within the context of people having more choice about pregnancy, the critical remaining piece is that the world is economically and societally absolute shit for people to have children in. Women don't just have the option of entering the workforce, they increasingly need to because a dual income household is now the market expectation in relation to cost of living in developed cities and especially cost of living with children in developed cities. Not to mention the capitalist class war overtly amplifying economic disparity instead of reducing it. Not to mention the environment, climate, justice, and social wellness being gradually destroyed by plutocratic christofascists on a grand scale.
TFR doesn't account for mortality which has also continuously fallen since then. If you're not adjusting for that, then you're looking at meaningless decontextualized numbers. Obviously if people want a certain number of children and the children keep dying then they're going to need to give birth more to get the right number of children. Birthing is not a useful measure on its own because pre-adulthood dead children lead to the same impact on population growth as no children in the first place.
I think your point is correct about the lack of optionality for women being in the workforce, but there are entire regions of the United States where it absolutely is optional. I live in one of them (Lynchburg, VA, which is filled with young evangelical Christian families that live in apartments and the mother stays at home) and my coworkers live in another (Salt Lake City, Utah which also has a ton of young moms staying at home).
I'm not foolish enough to think it's remotely possible in all places, but I do think an element of this is humans in the 21st century demanding a standard of living that far exceeds what they wanted in the 1970s, especially when it comes to vacations, automobiles, houses, etc.
My wife and I raised my first son (born when i was 23) in a 1 bedroom apartment, and my second child was born right after we moved into a 2 bedroom apartment. Most of my colleagues were shocked that I "didn't have a REAL HOUSE TO RAISE THE KIDS IN!!!! GASP!!!". And I realized then that many Americans have utterly warped ideas about the level of assets you need to have to enable family formation.
> And I realized then that many Americans have utterly warped ideas about the level of assets you need to have to enable family formation.
I agree with this. I also believe that modern people have become substantially...hmmm...dumber about expenses like food? People think it's impossible to make delicious nutritious meals quickly and cheaply, but in fact it's actually very easy and you just need to actually consider it as being possible, and you need to be willing to spend 5-10 minutes of effort. It's appalling to me the number of people who think that cooking anything beyond boiling water is mysterious or who will argue that it's impossible to eat well on a budget by pointing exclusively at niche products that only exist to satisfy a drive for extreme novelty and ignoring staples.
Awww man, I agree with you sooooo much on the food portion.
My son is now 19 years old, and doing very well financially (he chose to join the Army). I taught him from a young age how to shop and cook on a budget, in a healthy fashion. Started with hard boiled eggs, beans and rice, chicken and broccoli. Those kinds of things.
I also taught him (by observing his teenage friends) to always always always refer to DoorDash as a "Burrito Taxi" to help mentally reinforce the utterly absurd level of luxury you are indulging in when you have a human being drive a 3500 pound vehicle to your home to bring you a single meal prepared by somebody else.
The number of people I encounter who struggle financially (including one of my sisters) who indulge in these practices is insane. Our culture has forgotten that eating at restaurants (at least in the West, unlike say Singapore) is historically an expensive luxury, due to our relatively high cost of labor.
Agree, as a kid in the 1970s we ate almost every meal at home, cooked by my mother. Mostly staples rice, potatoes, vegetables, some kind of meat. Restaurants were a rare treat for something like a birthday or if we were traveling. Fast food, the same. Very infrequent, like maybe a few times a year would we be able to talk my mom into getting a Happy Meal. Pretty much the same experience for all the kids I grew up with as far as I remember.
We use agents very aggressively, combined with beads, tons of tests, etc.
You treat them like any developer, and review the code in PRs, provide feedback, have the agents act, and merge when it's good.
We have gained tremendous velocity and have been able to tackle far more out of the backlog that we'd been forced to keep in the icebox before.
This idea of setting the bar at "agents work without code reviews" is nuts.
reply