Treegarden

I tested it, history feature is per agent session, a cumulative history of all my agents would be nice.

If your boss is that bad, the correct long-term move is to leave, not to wish technology didn’t advance.

I mean is it not clear that companies are just an abstraction for a network of people, and you obviously must be be good with those people, ie seduce them into promoting you. And is it not clear that on the other side, you must keep your options open such that you find an alternative (job) if they are weird / toxic / dont like you / you dont like them?

This is not an easy question. It seemingly boils down to: what are fair ways to extract value from citizens for the shared value of the state?

However, the root questions are: what should the state provide, how much, and of what nature? A secondary question then becomes how important the redistributive aspect is. That’s what you’re seemingly alluding to when you say: people work, get taxed on it, but others automate that work and this automation does not get taxed.

Following that line of thinking makes sense, but it also contradicts the core benefit of automation, which is to delete non-needed work, make things cheaper, and make the value creator richer.

If the goal of redistribution is usually that “more” people reach a higher standard of living, then adding taxes and friction to processes like automation may conflict with that goal, given that automation is arguably one of the strongest natural drivers of higher living standards overall.

Of course, the counterpoint to “what and how much should the state provide” is “who should pitch in, and how much,” which is what you’re focusing on. I mostly agree that everyone should be taxed fairly, but I also see many exemption cases, because taxes are friction and we often want certain things to be frictionless. For example, I would oppose taxes on life-saving surgeries. But where do you draw the line? What about automation that indirectly enables or improves life-saving surgery?

I see a natural equilibrium with a tension: automation (also through AI) causes unit economics to drop and results in cheaper prices. At the same time, salaries for contributors grow because their impact is so high. So you end up with a new equilibrium of much cheaper prices and much higher salaries. What, however, about the people who can’t contribute? IMO the most natural and fair approach is to support (through whatever means) people’s “education”, allowing them to upgrade their skills so that they can contribute. IMO this leads to a new tension: not rich vs poor, or useful vs useless, but people who can up-level their skills vs those who don’t. And I think, at its extreme, it boils down to this: how much plasticity does your brain have? Because every other constraint, society can adapt or accommodate for.

I think by vibe coding he means taking these things at face value instead of rigorously looking if they are up to the standard. When coding you would rigorously look if the code is good / produces any bugs. With vibe coding, you give a prompt and just accept the output, which might be full of errors and blow up (or melt). The analogy is that, yes you can print airplane parts, but they were sloppy and just accepted them at face value instead of rigorously looking if they are up to the required (bug free) standard, ie they wont melt.

Can you elaborate how this relates to his own competency?

I don’t see how “tech” is limited to software. While your case might be made for software, according to many accounts Musk is a strong driver on the hardware side. For instance, I’ve read the Tesla and SpaceX books by Eric Berger, which are much more focused on technical things compared to the more mainstream books. And while Musk is not in the trenches with a screwdriver, he’s not faking it either.

To be honest, I’m actually interested in this hypothesis: is he legitimately skilled/knowledgeable, or is he indeed faking it? And for either side I would like to see evidence. This question is interesting to me because some of his companies have made substantial contributions to pushing the frontier of technology (reusable landing, high launch cadence, electric cars, energy).

If he is really faking it, that might even be good, because the success of his companies might be replicable and could continue without him. But what if he is not?

While your comment represents a common view, also here on HN, I find it bizarre: Hacker News is in part about innovative new technologies, and such new behaviours around them. For what it’s worth, in the last 5 years LLM have been extremely successful tech that has shaped society, maybe to the scale of the iPhone when it came out. Yet this comment is like the “I can’t believe everyone is staring at their phone in the subway instead of talking” trope or “this couple is on a date but they’re just on their phones.” On Hacker News I would expect people to be more open to such new behaviours as they emerge, instead of kind of kink-shaming them. I myself talk hours to ChatGPT, and am astounded by this new tech. I certainly find it better than TikTok (which after trying out I don’t allow myself to use).

I dont disagree, but you can horizontally scale a monolith too, no? So scaling vert vs horiz is independent of microservices, its just that separating services allows you to be precise with your scaling. Ie you can scale up a compute heavy micorservice by 100x, the upload service by 10x but keep the user service at low scale. I agree that one can vert scale, why not. And I also agree that there are probably big microservices. At my last workplace, we also had people very bullish on microservices but for bad reasons and it didn't make sense, ie ideology.

I fully agree on workplace politics, but for system design interviews, are you not also just supposed to ask your interviewer, ie give them your premises and if they like your conclusions? I also understand that some companies and their interviews are weird, but thats okay too, no? You just reject them and move on.

Im no world leading expert but as far as I understand, coupled with events, if an unimportant service goes offline for 5 min (due to some crash, ie "fault"), its possible to have a graceful degradation, meaning the rest of the system still works, maybe with reduced ability. With events, other systems simply stop receiving events from the dead service. I agree you can achieve a lot of this also in a monolith with try catch and error handling, but I guess there is an inherent decoupling in having different services run on separate nodes.

I dont quite follow. I understand mono vs micro services, and in the last 3 weeks I had to study for system design and do the interviews to get offers. Its a tradeoff, and the system design interview is meant to see if one understands how systems can scale to hypothetical (maybe unrealistic) high loads. In this context the only reason for a microservice is independent scaling and with that also fault tolerance if an unimportant service goes down. But its really the independent scaling. One would clearly say that a monolith is good for the start because it offer simplicity or low complexity but it doesn't scale well to the hypothetical of mega scale.

This is a catastrophic moral failing on who ever prompted this. Next thing they will ban chatgpt from teaching you stuff because its not a certified licensed teacher. A few weeks ago my right eye hurt a fair bit, and after it got worse for 24 ours, I consulted chatGPT. It gave me good advice. Of course it sort of hallucinated this or that but it gave me a good overview and different medications. With this knowledge I went to my pharmacy. I wanted to buy a cream chatGPT recommended, its purpose being a sort of disinfectant for the eye. The pharmacist was sceptical but said "sure, try it, maybe it will do good". He did tell me that the eye drops that gpt urged me to get were overkill so I didn't get those. I used the eye cream for some days, and the eye issue got better and went away as soon as I started using it. Maybe it was all a conincidence but I dont think so. In the past gpt has saved me from the kafkaesque healthcare system here in Berlin that I pay ~700 a month for, by explaining a MRI result (translating medical language), background info on injuries I've got such as a sprained ankle, and recovery time scenarios for a toe I've broke. Contrast the toe experience with the ER that made me wait for 6 hours and didn't believe me until they saw the X-rays, and gave me nothing (no cast or anything) and said "good luck". The medical system in germany will either never improve or at a glacial pace, so maybe in 60 years. But it has lost its monopoly thanks to chatGPT. If this news is real, I will probably switch to payed grok, which would be sad.

Well, let’s assume you’re correct about all that. To me, it seems he was already quite rich before doing all the Trump-related things you mentioned. Those might have made him richer, but I’d suspect they didn’t move the needle much compared to his real profit centers (probably Starlink and Tesla). If anything, I’d argue those actions made him poorer by further damaging his reputation. And any “power grab” motives he may have had likely evaporated after his fallout with Trump. One current example is exactly what sparked this thread: the NASA Chief seemingly trying to impress Trump by attacking SpaceX.

The tone of voice suggests you dislike Musk, but I will still answer in good faith. From what I can see from the outside, he has consistently for many years stated the same goals and worked on them. Any or most financial gains he made, he invested into his companies which work on accomplishing those goals (for example, going to Mars). The most notable example was investing his PayPal money into Tesla and SpaceX when they both were at risk of going out. He also has a reputation for working a lot, though it may be exaggerated, but he looks fairly unhealthy so maybe not too far off. Compared to other super rich people, he seems to spend less time in lavish ways, for example on yachts or similar. He probably still spends more money than we can imagine on unnecessary things, but on the spectrum of rich people he doesn't seem to be the most frivolous. Finally, he has said on Twitter that he doesn't care about money but needs resources for his goals, for example going to Mars. And after everything I’ve seen and the examples listed, it doesn’t seem totally implausible that he means it.

I mean, just as the phrase goes "your terrorist is my rebel," one could say "your propaganda is my information." That's exactly why a decentralized system matters. It doesn't just resist capture by a single authority, it allows competing narratives to exist side by side. What one group sees as misinformation, another might see as essential context. The goal shouldn't be to eliminate bias entirely, but to prevent any one group from controlling the flow of all information.

I agree with you on several levels, what we call “exceptional” is entirely dependent on the metric we choose. Every species excels in its niche, and human exceptionalism is just our own preferred framing. It's fair to say it often functions like supremacism: a belief in our moral or functional superiority over other life forms.

That said, in a world of scarce resources and competition, tribalism and “team-thinking” are not bugs, but features, evolutionary tools for survival. From that lens, human supremacism isn’t a moral claim, but a pragmatic stance: of course we prioritize our own species. We are team human.

As for whether we're destroying the planet, it's a complex picture. I'd recommend False Alarm by Bjorn Lomborg, it pushes back against overly apocalyptic assumptions and argues that while climate change is real and serious, we're not necessarily headed for collapse. Doesn't excuse inaction, but does complicate the narrative.

I agree and dont understand the OP. I drink coffee out of the fear that I would waste my whole days time. The coffee allows me to spend some hours of focus time on what I want. In line with the blog posts point. This has been a struggle to all my life, its very hard to control my focus, my attention. I've been diagnosed with adhd (for whats that worth) and at some point took medication who's whole purpose was to allow me to control my focus. When I have unbridled focus, I suddenly have access to my brains full capacity. I think my IQ is easily 10 or 30 points higher / lower depending if I have focus or not.

It was but so were other models before. OP said the twitter to grok feature is a good use case and I agree. Its great for fact checking. For example it will debunk conspiracy theories and misinformation tweets in general. I even asked it about its own hitler meltdown and it rejected its own words (so I must have asked it after they fixed it).

internal motivation means that someones acts without external stimuli, their drive comes from within, its internal. External motivation means that an external stimuli is used to make someone act. I.e. a monetary reward, or validation etc. When someone is internally motivated, they can have a stable state. When external motivation is introduced, it can replace the internal motivation and will. Now what happens when you then lose the external motivation, the external stimuli again? The internal motivation is gone and this means all motivation is gone, the act stops.

On top of this, some people say motivation is cheap, discipline is what matters.

Who decides what is moral? For which moral causes are our contributions beyond a drop in the ocean? I can go work in a soup kitchen, but thats not gonna help thousands or millions of people in need. There is a structural reason why a certain fraction of society becomes in need of a soup kitchen. Can this not be applied to anything? War, famine, natural disasters, poor people that need a lawyer. All these are the result of structural reasons. Can these structural reasons be solved or are they part of the human condition, even part of nature? Manually helping 1+n people in this would not address the root cause. Try to do a scalable solution, but those are hard and I guess most that would wok have been tried. In my childhood I would have needed a tutor, my teachers where terrible. Yet it was not the tutors that would help me now, it was chatGPT. Should I now become a tutor, should I build a openAI competitor, or should I build tutuorAI? If I do marketing at tutorAI will this be a bullshit job? When I build an app, sooner or later I have to solve abstract array puzzles, solving these will make the app work. Work often becomes abstract. Does it mean its now bullshit? If everyone worked at the soup kitchen, would homelessness be solved?

Well it comes in phases. Last year I read a new book every few days. I probably read 30 books or so, then I got sick of it and stopped. Haven't read a single one since then but also dont care too much about it.

I've found watching a tv series and reading a book are very similar. They both share two key issues:

First reason there are good and bad books, and finding the good ones is really difficult for me. Just like with a tv show, I will stumble on a book and read it, it will be a great book that really moves me and makes me think. Now hooked on books, I will look for more books. I will read one after the other. I will eventually find one thats tiresome or "bad". I will fight through it. But then when the next book is also not great, I will stop entirely. Exact same happens to me when watching tv shows (last great one was succession).

---

Second reason is just getting sick of the medium in general. Like with many things in live I just get sick of reading. It also happens to me when I regularly watch tv shows, at some point I get sick of the activity all together and stop for a few months (or years).

From what I followed, its because: They already send payload to space with the falcon rockets (reliable cash cow) and the only point of starship system is proof of concept of full reusability. There is no point to the whole project if they dont achieve this. They are constrained in launches, either through regulatory (FCC) or engineering timeline and so far, every launch counted. They achieved a substantial improvement.

If they dont catch the starship (upper stage), the whole project is pointless so its important keep things simple (details like payload door, cargo dont matter) until they achieved the whole loop (land & catch starship)

They already have a cheap way of launching. Cheap for current market rate. Whole point of this project is to improve cost by / 1000.

They achieved substantial progress with every flight. 1. It flies, 2. hot staging 3. reach orbit 4. land both & heat shield, 5. catch booster, 6. extreme conditions & improve heat shield.

I too ran into that issue as I nearly cut all sugar from my life since 6 months. As the other pointed out, here is my alternative, which is great [0]! I once drank it raw, it was terrible. But usually I blend it with the European version of Soylent powder and then it tastes amazing. 1. https://www.natureletics.de/products/natureletics-pure-natur...

Nice answer, but I can counter: I'm high performing, doing high impact work. For some reason I need to analyse user reviews that use slang. I can't look it up because UD is blocked. Insanity. Maybe our hot new product is suddenly in the crossfire of some meme war. Eg. kids doing weird stuff on tiktok. Can't look it up. There are examples with companies going into fiascos because they publicly respond out of touch or awkwardly to event on social media. Opposite is that viral twitter account of wendy's. Do they have UD blocked?

Funny, I actually go frequently to one or two of these, since I live in Berlin. I pay 42% taxes and still these government pools are not only a bit pricy (no discount if you want to go regularly) but they have terrible, irregular opening times. They will spontaneously close down for a month, without notice on their site or google maps, only putting a sheet of paper on the door. They will rotate opening times randomly. Even worse, they are not open (only charlottenburg, which is small) for around 6 months in the summer. This is because youre supposed to go to the outdoor pools but I want to go at 6pm after work when they close and even if they are open they are too cold. On hot days they might be fun but then they are notoriously overrun but low education bracket people that get into fist fights so vehemently it was a big topic in berlin this summer. As a response there where then a bunch of police people hanging out at the pool and now you need to show your id before entering.

Something vaguely similar happened in Berlin: They banned parking rental 50cc scooters on the pavement, they have to be parked on the street, competing for parking with cars. To me this is a terrible rule, completely out of touch. Scooters improve the city as they are electric, small, and less dangerous to others. I have a car and in the summer I often pay a few euros to rent those electric 50cc scooters because they are really nice. However, one of the major benefits is that you can park anywhere.

There is a designated strip on the pedestrian walkway where it used to be allowed to park them, currently its only allowed for bicycles. There is more than enough room there and as its on the side it bothers no one. So banning them from there is not necessary.

The real problem we have is not even about these specific 50cc scooters but about the smaller ones that are mentioned here. Which have not been affected by this ban. The real problem is that some bad people, maybe its the tourists, literally park them in the very middle of the walkway, blocking people and being terribly annoying. And for this, the solution would be harsh punishments. Eg. when someone parks their scooter this way they have to pay a massive fine or get banned or whatever. Maybe users could report them and get a bounty.

So, while there is a real problem, the politicians, where I live, made this terrible decision. And when I came home, exhausted from work, there was actually parking right in front of my doorstep, but it was blocked by two rental scooters.

Something vaguely similar happened in Berlin: They banned parking rental 50cc scooters on the pavement, they have to be parked on the street, competing for parking with cars.

To me this is a terrible rule, completely out of touch. Scooters improve the city as they are electric, small, and less dangerous to others. I have a car and in the summer I often pay a few euros to rent those electric 50cc scooters because they are really nice. However, one of the major benefits is that you can park anywhere.

There is a designated strip on the pedestrian walkway where it used to be allowed to park them, currently its only allowed for bicycles. There is more than enough room there and as its on the side it bothers no one. So banning them from there is not necessary.

The real problem we have is not even about these specific 50cc scooters but about the smaller ones that are mentioned here. Which have not been affected by this ban. The real problem is that some bad people, maybe its the tourists, literally park them in the very middle of the walkway, blocking people and being terribly annoying. And for this, the solution would be harsh punishments. Eg. when someone parks their scooter this way they have to pay a massive fine or get banned or whatever. Maybe users could report them and get a bounty.

So, while there is a real problem, the politicians, where I live, made this terrible decision. And when I came home, exhausted from work, there was actually parking right in front of my doorstep, but it was blocked by two rental scooters.

I appreciate the nice feedback!