Sure let me do that. Can I post this as a ShowHN if its just video? The rules say people need to try out but that will cost me a small fortune :) ...could perhaps post on Github and people can setup the repo themselves with their own Openrouter key if that works. Have never done a ShowHN but would be fun to try it.
I've been thinking a fair bit about what I'm seeing in terms of the output I experience
It's quite hard to quantify, but I think it's one shot nature really makes it hard to gauge it's capability
Friends have spoken of good days and bad coding days with me, and I find it odd nodding along, it's a strange new normal
At times it feels like we're just coding with one-armed bandits, trying to carefully line them up for a jackpot and just discarding and retrying if we don't hit
I think about some of the more complex systems I've built and I wonder how well we can build them like this
And over engineering, there seems to be over engineering everywhere, and yet, more fragility to our systems
I imagine this stuff is probably really good at iterative changes to improve objective benchmarks like CPU or RAM use. I'm thinking of little contained optimizations that you can understand in and of themselves, that you maybe have done yourself before in other places, found really quickly and applied uniformly. Stuff you can confirm to be what you expect it to be by mostly just scanning. Low hanging fruit for sure, but something where you can actually know what is a fruit and what is crap, and only keep the fruit, and develop some confidence in the process, if that makes sense?
Or trying to reduce complexity, increasing readability and coherence of variable names (the opposite of code golf if you will), while staying within a certain limit of performance regression (e.g. "make this code as nice as you can while making it at most 0.5% slower").
Making the stuff millions of people have been using for decades better, in a way that also makes it better for humans when they read the code. Surely that's possible, some people are probably doing it but it doesn't go viral as much, because it's too mundane.
And of course, making new stuff is more exciting. I mean, you could hit on something with a vibe coded thing, and then know it's now worth to make a non-sloppy version, but you won't get much fame for making ffmpeg twice as fast by prompting an LLM. Though on the other hand, it's like a safe investment (if not in "fame", then in "improving the stuff we all have to use daily"), because you know ffmpeg and many many other things will still be around, whereas a vibe coded thing that wasn't special will be 100% forgotten the next day, or have just the one user forever.
I'm going to engage with you a bit because this situation does read to me like people talking past each other and I personally don't like when I see that happening
I'm going to state some assumptions up front and I appreciate if they seem incredibly simple and or naive but I find it's useful to have a common frame of reference in these situations
Reading what you wrote, I think it's plausible that you don't seem to realise that the disagreement that your getting into with people is one that's deeply emotionally charged and the current zeitgeist of how we engage in disagreement these days being predominantly meta disagreement means the vast majority of people are pattern matching on situation, context and vibes than what's said is the norm
I'm not a fan, but I absolutely can recognise and acknowledge that for a lot of the people who are coming into forums like this looking for civil discussion, this meta argument is very much what they retreat to unless they feel like it's worthwhile engaging with someone else honestly and vulnerably, because the dominant tactics of online disagreement are all about managing and depleting the energy of the person who you disagree with instead of engaging with them, while at times doing so in a way that makes them look unreasonable or foolish to the wider audience or signalling to that wider audience so that they're in on the joke as it were
So given that context, your argument will read to many as engaging in that style, and as a result they really don't want to engage with you on the merits of what your saying
If you want to really get engagement from people now, which I believe you want to on charged topics like this, you usually have to act in a way that falls outside the pattern, which requires some thought and effort
We're really cynical these days and dislike wasting our time and energy, not so much because I think we care about the time or the energy, I've seen a lot of people still just arguing back and forth and can't help thinking to myself that if they were willing to put that energy into arguing so much why didn't they try something else that might have had a higher likelihood of success
But at least in my view, we don't want to be as vulnerable anymore, too many people have put in the time and the energy of disagreeing in good faith sincerely believing that they were speaking with someone and reaching for understanding only to later realise that the other person they were speaking with was just running an algorithm, probably not even a very sophisticated one at that
And I'm not immune to this either, it's not fun, this dominant cynical strategy of our age
It stifles legitimate and interesting discourse and prevents us from working towards better understanding each other in what I don't think anyone will disagree with saying are trying and difficult times
My personal reaction to it is stuff like what I'm doing here, jumping into a discussion when I see people speaking past each other and when I've got the capacity arguing for a pause and a change in approach and then leaving it up to them as to whether they want to do that
I'm directing this at you not because I think you're particularly at fault, just that I think you've got the most capability to shift the conversation by changing how you are responding
I could be wrong, maybe you don't want to, as is your right, or if you do people will still engage with you poorly believing that you aren't speaking in good faith, as is theirs
Thank you for your time if you read this, hopefully it leads to a more productive discourse
> So given that context, your argument will read to many as engaging in that style, and as a result they really don't want to engage with you on the merits of what your saying
On the contrary, everyone is engaging timr within the scope of the exact challenge that he himself designed. Repeatedly, he has refused to answer his own question while insisting that he has. It's pretty wild.
> The only question I have asked is for you to make an affirmative argument.
You asked us to consider the reasons why conservatives vote for politicians with platforms built on the hatred of immigrants, besides hatred of immigrants. Remember?
> You asked us to consider the reasons why conservatives vote for politicians with platforms built on the hatred of immigrants, besides hatred of immigrants. Remember?
No, that is literally not what the comment said. I'm actually sort of amazed that you can get that from what I wrote, and treat is as some kind of "gotcha", when it's the top of this thread, and literally the same message I've been repeating throughout:
> Or maybe, when you say that the platform is “built upon hatred”, that’s just your opinion, and the other side actually has reasons that you haven’t bothered to consider?
> I don’t like this policy, but engaging in exaggerated rhetoric, then calling the other side liars because they disagree with your rhetoric, is everything that is wrong with political debate in the US right now.
To wit: stop calling people liars. Make an argument instead.
The fact that the current US administration lies is indisputable. I'm not calling them liars because they "disagree with [my] rhetoric" but because they have been shown to have repeatedly lied. Saying that Trump is a liar is not "calling names" but reminding of a well-known fact. But ok, I'll indulge your bad-faith argument:
1. The administration has claimed to oppose only illegal immigration in order to encourage legal immigration. [0]
2. The administration has consistently lied about and demonized immigrants who came legally. [1]
3. Recent policies have made legal immigration more difficult. [2]
4. The effect of these policies will be to reduce legal immigration, contradicting the administration's earlier stated goals. [3]
5. The administration has repeatedly expressed white nationalist sentiment. [4]
I didn't ask you to make an argument that the administration has lied. That's trivial. And though you're getting closer with "the administration has lied about immigration issues in the past", again, that's trivial and non-responsive. And telling me that the administration is against immigration is telling me that water is wet. So what if they are? Elections have consequences, and this is not a sudden discovery.
I asked you to rebut the arguments in front of you, instead of just calling people liars. It isn't hard, if you're even a little bit intellectually curious. I'm tired of responding, so I'll just model the behavior for you, and then I'm done.
First, five reasonable arguments against this change, none of which involve calling people liars:
1) It targets the very people who are most likely to contribute positively to US society.
2) It's clearly against the intent of the original status adjustment legislation.
3) If it's actually applied to H1B visas (which is unclear), it's clearly against the intent of the 1990 immigration reform act, which established dual-status visas.
4) It seems intended to eliminate / dramatically reduce green card issuance without legislative intervention. I am against this because it is unconstitutional.
5) It discourages smart people from moving to the USA.
OK, 6:
6) It's especially cruel to families where one family member is already a US citizen or permanent resident.
Now, five arguments in favor of it:
1) It's appropriate to ask people on non-immigrant visas (e.g. tourists, students) to return home at the end of those visas, rather than creating a limbo class of people who are sitting around waiting for status transitions, which is both real (i.e. I personally know people in this situation) and a problem.
2) It distributes the review load around the world. Obviously true.
3) It was never the intent of the 1960 status adjustment legislation to allow non-immigrant visas the ability to transition directly to permanent residence.
4) However blunt the approach, it does eliminate a major incentive problem for gaming the short-term immigration system, if you know that you have to return to wherever you came from, and wait for approval.
5) While I don't think it's appropriate to make this change for pending applications (and to be clear: we don't know if that's what's happening), I think it's completely fair to announce it as a policy change going forward.
Okay, I'm surprised by how much you are missing the point, so let's imagine a dialog taking place in the 1930s in Europe.
A: Hey, I think we should murder all people of <ethnicity> because they are a threat to national security.
B: I think that your argument in favor of genocide is based on animus and not offered in good faith.
A: How dare you call me a liar! Why don't you actually engage with my argument??
Sorry for the crude analogy, but that is what you are saying. You are completely missing what is shocking about this scenario.
Everyone already knows the arguments for and against legal immigration. We've been having that discussion for decades, or centuries, and there are valid and coherent arguments on both sides. There is no need to reiterate them here.
What is unique about the current situation is that the current administration is not engaging with valid arguments against immigration: they are offering transparently nonsense justifications, which we are not used to seeing from our government to this extreme degree -- even the bad-faith arguments for the Iraq war were dressed up in real argument clothes. No matter how you feel about immigration, you should be shocked by the administration's behavior. Not just that the arguments are unreasonable, but transparently so. Pointing that fact out is completely relevant, as it is IMHO more novel to our society and dangerous to democracy than simple immigration policy. Furthermore, treating the administration's arguments as valid just gives them legitimacy, which they do not deserve.
The people in favor of these policies are not making thoughtful decisions for the good of the nation and it does no one a favor to pretend that they do. They will not be persuaded by the well-reasoned arguments you point us towards because reasoning is not part of their decision making process. That's why everyone in this thread is calling you a tool, and why pointing out the bad faith is completely relevant.
I appreciate the thoughtful reply. I don't think I'm "talking past" the people I'm replying to -- I understand exactly what they're saying, I get that these are emotional outbursts, and I'm simply trying to re-iterate the futility of it, in the hopes that someone will get it -- but I do agree that it's likely pointless and probably a waste of time.
> It stifles legitimate and interesting discourse and prevents us from working towards better understanding each other
We definitely agree on this.
> So given that context, your argument will read to many as engaging in that style, and as a result they really don't want to engage with you on the merits of what your saying
If we are at a point where "do not call people names instead of arguing" is considered a tactic or a style, we really are doomed.
> but I do agree that it's likely pointless and probably a waste of time
To briefly clarify, I don't believe it's pointless, that wasn't what I intended to convey, what my position is, is that the current mode of communication demands more of us, so as a result at least I and people like myself engage with it less often, but when we do, we do so wholeheartedly and if it looks like the other party isn't engaging in good faith, try a little, but are willing to wrap up, at least in my case after taking a few stabs at it
I personally find that this strategy both makes me feel more empowered and engaged in these situations as well as gives me hope that if my strategy is more sustainable, then it will slowly be adopted, which is good, I would be delighted to engage with someone who's also following this approach or something like it
> If we are at a point where "do not call people names instead of arguing" is considered a tactic or a style, we really are doomed
I don't think it's quite that negative, from my perspective this has become a very negative value game (in the Von Neumann sense) and being mindful of the fact that it is very much being treated like a game, adopt a strategy that allows for people to engage with it like discourse, deescalate and clearly signal my willingness to engage with the other party, yet however still be a reasonable move in that game are all goals that should be met when I communicate in these sorts of contexts
Given there's likely multiple other ways to hit those objectives, the route I'm taking only being one of them, I'm satisfied to continue tilling the odd windmill here and there
Once again, thanks for engaging, have a great day!
> This is the part I struggle with when I think about it. Years of identity rests on “I am someone who writes code”. That identity is now contingent on a tool stack that’s three years old and could regress. If it breaks, the identity goes with it, and I’m fine with that.
> I think that’s the most honest signal I can give about what I actually valued. The thing I was doing all those years wasn’t writing code. I was making decisions and watching them become real. The agents make that loop shorter. Take the agents away and the loop becomes too long again. I’d rather do something else.
What's really interesting to me and I'm honestly curious as to how many people are in the same boat as I am vs the author is that I have the same feeling and I'm not ok with it
I think if LLM's disappeared tomorrow I could go back to coding without them, however there'd be that transition of scraping the rust off and honestly I don't like that
It's really discomforting to feel like the codebase I'm working on is getting ever more foreign and strange, especially as LLM's when they communicate with you are persuasive that they are making things better, and they do work, for a given value of work anyway, it's really hard at times to tell looks right from is right
I've come up with some strategies that mitigate this to a degree and I'm slowly trying to find more
I think a lot of people are taking refuge in practices, but aren't entirely coming to terms with the actual scale of the difficulty of writing correct code, skating by on it being useful, which don't get me wrong isn't a bad thing, our clients pay us for creating useful things
Not turning flops into heat
However I get the uneasy feeling like our tools are very inadequate
Types measure consistency, not correctness
Tests and code coverage are very easy to game, and unless you've put in the discipline of creating something on the order of sqlite's test suite, there's likely to be an ever growing pool of latent footguns sitting in the code you're making
And I'm not saying this to be negative or alarmist, at the end of the day it depends on what your goals are, and most working devs and startup folks are just trying to ship
And we can't really argue that for many, they do help do that
You will ship
Something at least
I find myself in this odd position of acknowledging that the coding world has shifted in ways that I find exciting and strange, and as much as I've begun to understand how to navigate this new environment, the part of me that felt deeply grounded in the things that I built is still feeling disquiet
> LLM can basically convince any one of anything
This and revision to the mean I think are real problems
I've found myself on more than one occasion just stepping away and needing to really sit down and think and to not ask an LLM until I have a clear idea of what I want to do
The one thing that bothers me is that one process I really used to run is thinking in code, slowly sketching out a solution until it had the properties I wanted it to have
I find myself not really engaging with this at present and it really bothers me, I've been trying to figure out how to get back into doing it again because I think the most differentiated and interesting ideas and thinking I had were usually shaped by going through that process
However so far I've found working with LLM's just doesn't jive with that thought process and several months into using them I'm still figuring out how to go back to doing that
I can't help but feel like these things sort of exist already in imperfect forms, so the question that comes to mind is one of costs, specifically what costs does interacting with or using such a network impose that makes it not worth it for people to engage with it in bad faith
Which immediately raises the question of what constituents bad faith interaction?
I think the author is at least saying that content created for the express purpose of pushing products is a bad faith interaction they don't want to engage with, cool, I'm not exactly a fan of ads myself
So what are different kinds of ecosystem that are resistant to bad faith interactions and why?
Academia is one to a degree, that's one kind of space where doing this kind of bad faith interaction would receive pushback, so it becomes not worth doing, that's one kind of negative feedback cycle, I think to a degree HN has a similar dynamic of the censor backed with moderation, the cost here would be the space constantly working to keep itself "pure"
My understanding is 4chan and it's like are another, their strategy is to create such a hostile environment that capital has limited interest in engaging with it, all you get are "authentic" interactions, though I'm not going to pretend I've spent much of any real time on there, so this is at best based on second hand experience, the cost here is more interesting, how hostile an environment are the users willing to bare and perpetuate in order to create their safe haven?
Then there's non-standard technical spaces, I'm less confident than the author that you can create a real alternative web without paying a tax on some level, what I mean by that is if you're building a protocol, it has on some level to be hostile or it's going to get co-opted, what comes to mind is something more like a multimodal protocol, you don't send text, you send media the vast majority of the time, VNC for example might work, your clients register click and hover states in 2d space and your servers are basically game engines, it would be very technically hostile, however until AI tools get a lot better, there's really little for them to work with and taking and remixing content is now fully on the authors terms, the downside is this might be worse, because it is very limiting and completely against the principles of what the web was built on, so if capital ever decides that they value this new space there's a lot they can do here
Am alternative tax is going fully into the p2p world, we build a network based on caching and p2p sharing and tracking anonymous metrics of how much content has spread, or who in the network has
S it, that would at least indicate if it's something widespread or if it's something people who you trust engage with, this will make a network of gaps, where the cost is potentially even more fragmentation, however you can at least trust that some people who you know are on some level vouching for the content you see
It's a hard problem, I'm interested if this reframing on costs gives people a better way to think about it?
Just realised that reading your message, I really feel this, I've been designing a game and I've recently been having discussions with friends and people interested in it and it's just a really different experience talking with them vs posting about it, don't get me wrong, having a weekly cadence is nice and Sharing Saturdays can be really helpful to get the word out there, but it's such a different interaction and mindspace I end up in during the "plan to explain to people in this weird advertising, but not process about my passion project", vs "talk to someone about my passion"
And I'm aware that these are different activities, but I don't think they should be as far apart emotionally as they end up being?
For example the last discussion I had we talked about how I was exploring connecting the impact of actions in the small scale to the large scale, for example how designing a particular construct or vehicle, would change how efficiently a player would be able to mine and that would then impact how much that particular player made from mining in that area
This creates all sorts of interesting questions and even just that discussion was engaging
The reason I've been querying the 1 hour is a user's quota resets are often longer than that, as a result I've seen situations where someone builds a large context, then hits their quota limit, waits 2+ hours, their cache is gone, their first message then eats 20%+ of their current session quota and the user doesn't want to compact as they're still trying to get the model into a good understanding of the problem, this seems to be a really painful consequence for users on anything less than a max plan which seems like an unintended consequence of Anthropic's own system design choices?
IE How their quota and caching interact with each other, it doesn't make pro and max a little different, it makes it significantly different by unintentionally penalising pro users
reply