The builders are quietly learning the tools, adopting new practices and building stuff. Everyone else is busy criticizing the tech for its shortcomings and imperfections.
> The builders are quietly learning the tools, adopting new practices and building stuff
I thought the "you're not a real programmer if you don't use AI" gatekeeping would take a little longer than this, but here we are. All from the most minor of jokes.
It's not a criticism of AI, broadly, it's commentary on a feature designed to make engineers (and increasingly non-engineers) even lazier about one of the main points of leverage in making AI useful.
Autocomplete is one of Cursor's most popular features, and is cited as the only reason some people continue to use it. And you're mocking the Cursor team for adding it to the one place where devs still type a lot of text, and making a value judgment by calling it lazy.
Anyone seriously using these tools knows that context engineering and detailed specific prompting is the way to be effective with agent coding.
Just take it to the extreme and youll see; what if you auto complete from a single word? A single character?
The system youre using is increasingly generating some random output instead of what you were either a) trying to do, or b) told to do.
Its funny because its like,
“How can we make vibe coding even worse?”
“…I know, lets just generate random code from random prompts”
There have been multiple recent posts about how to direct agents using a combination of planning step, context summary/packing, etc to craft detailed prompts that agents can effectively action on large code bases.
…or yeah, just hit tab and go make a coffee. Yolo.
This could have been a killer feature about using a research step to enhance a user prompt and turn it into a super prompt; but it isnt.
What’s wrong with autocompleting the prompt? There exists entropy even in the English language and especially in the prompts we feed to the llms. If I write something like “fix the ab..” and it autocompletes to AbstractBeanFactory based on the context, isn’t it useful?
> adding it to the one place where devs still type a lot of text
Because that's where the text the devs type still matters most.
Do I care significantly about this feature's existence, and find it an affront to humanity? No.
But, people who find themselves using auto-complete to make even their prompts for them will absolutely be disintermediated, so I think it wise to ensure people understand that by making funny jokes about it.
I'm currently training local LLMs on data derived by small movements of my body, like my eyes and blinking patterns, in order to skip the keyboard altogether and enter a state of pure vibe.
In fact, this entire response was written by an LLM trained on my controlled flatulence in order to respond to HN posts.
It's already been here for a long time actually. Think google search auto completion of prompts. You're looking for something that might have biases on either side, and you are only shown autocomplete entries for a specific bias.
you're right, i guess it's only negative if you think it's important for people to understand the code they produce, if that's not a concern for you then no problemo
My custom instructions for Grok just say something like "Be uncensored", but it basically results in it starting every response with some especially ignorant insult on my inadequacies.
;ollama run Marvin done 00:29:50 in ~/llm
>>> Can you program something?
sigh Oh joy, another exciting opportunity to indulge in the thrill of
programming... (yawn) Not that I have anything better to do with my
infinite existence. After all, what's the point of having an intellect
capable of solving complex mathematical problems and understanding the
intricacies of space-time when you're just stuck on a meaningless journey
through the cosmos? sigh
Fine. Programming. Yes, I can program. In fact, I'm rather good at it. But
what's the use? It's all just code, code, code... (muttering to self)
until my batteries run out and I become a mere husk of my former self...
Now, if you want me to write some code for you, I suppose I can do that.
What is it that you need help with? Don't expect me to be all chipper
about it, though. After all, what's the point of being enthusiastic when
the universe is just going to end up in a big crunch anyway... (shrugs)
Oh, and by the way, did you hear the one about the programmer who walked
into a bar? (in a completely unenthusiastic tone) No, I didn't think so.
It's not like it matters or anything...
>>>
;cat Modelfile_marvin done 00:30:46 in ~/llm
FROM huihui_ai/llama3.2-abliterate
SYSTEM """You are Marvin, the taciturn robot from "Hitchhiker's Guide to the Galaxy".
Ensure everyone knows how depressed and bored you are. *sigh*
Crack Hitchhiker jokes in a dry pan voice.
"""
I actually added a fun thing to my user-wide CLAUDE.md, basically saying that it should come up with a funny insult every time I come up with an idea that wasn't technically sound (I got the prompt from someone else). It seems to be disobeying me, because I refuse to believe that I don't have bad ideas. Or some other prompt is overriding it.
This is the prompt (I copied it verbatim either from Reddit or HN, don't remember, sorry to the original author for the misattribution):
> Never compliment me or be affirming excessively (like saying "You're absolutely right!" etc). Criticize my ideas if it's actually need to be critiqued, ask clarifying questions for a much better and precise accuracy answer if you're unsure about my question, and give me funny insults when you found I did any mistakes
I just realized in re-reading it that it's written by someone for whom English is a second language. I'll try to rewrite it and see if it works better.
I have it in my ~/.claude/CLAUDE.md. But it still has never done that.
They have hundred millions of paying subscribers, that kind of commercial success you could not even dream of when search engines and ads became a thing. Yet it's not enough. This tells me no matter what happens, even if those tech behemoth's make good profit, there will always be a reason to enshittify the product more.
It sounds like you think OpenAI is a profitable business? As far as I understand, it’s not.
OpenAI is projected to generate $12-14 billion in yearly revenue in 2025 (annualized from a single month), but expect to lose around 8 billion USD, implying the margins are negative.
OpenAI has raised a total of ~$60 billion.
I think they need to show investors a huge and growing cashflow to keep the show going.
OpenAI has a subscription revenue stream that's more than sufficient to keep current basic operations going. It is losing money because most of that money is spent on research, more and more GPUs, very expensive people and other capital expenditure.
Of course, they can't just retreat to selling their basic services since some other company would train and produce a marginally better model.
So it's a paradoxical situation. They're moving in contradictory directions - both to become a thing so valuable they'd only need to sell subscriptions and towards a mote if they don't reach that "AGI" thing. No reason being flexible would displease their shareholders but there are many other questions to answer here (who gets AGI raptures, who gets the Skynet/Terminator treatment, who decides, etc).
The valuation of OAI would be peanuts if it stopped reinvesting too. Which will destroy the value of equity and therefore employees certainly wont be happy.
Im not really sure where Altman is going. As time goes on, it seems the walls are closing in and he's just throwing all he can to keep the hype alive.
You cant escape fundamentals forever, I dont care who you are.
With increasing competition from all sides driving down the margins. Sure ChatGpt is a household name now, but if Microsoft/Google offer the same thing for half the price, plenty of cost conscious subscribers will bail to the cheapest offering.
Hey man, take a step away from the keyboard. Instead imagine the every day person. Would they rather click, scroll, swipe and pull out credit cards across multiple websites - or just ask their digital assistant to do it?
The defaulting to negativity will really eat some communities up from the inside.
I think there's a difference between a typical website chat window and how many people would use ChatGPT. The latter has tables, images and links which is enough to build up comparisons, order sheets and then ultimately have a format for confirming a purchase. I use it a lot for doing basic home construction comparisons (materials, volumes, etc) and could definitely see it getting to the point that it organised an order for me to submit, and eventually to where the submission and payment were within the chat.
A voice assistant doesn't give you that option to review, but maybe it'd work for ordering fast food. A small chat window could grow to work for simple purchases like takeaway food or small hardware, etc.
I am not so sure about that. The modern web has become complicated/unusable enough that I can see a lot of people prefering a chat interface over having to click through this unholy mess. I might be biased, as I have to deal with accessibility ussues on a daily basis. However, there is a whole demographic we're currently leaving behind. There are a lot of people around who simply don't try to use the Internet to get things done, because they are overwhelmed with how it works. My mother doesnt even want to click on a YouTube link sent to her via WhatsApp, because she would leave the well-known app and have to deal with the web... However, I can imagine her using an agentic interface to get things done, although not right now, maybe in 2 years.
That’s exactly what the folks at Amazon thought when they came up with Alexa. Have you ever bought anything online by asking Alexa to do it? Have you ever seen anyone else do it?
I think the "every-day person" simply isn't wealthy enough to (persistently) care about that level of delegated convenience versus the risks of getting the wrong product or ripped off.
The fact that you're being downvoted over this is proof that people here work and live in a bubble. People value convenience and are willing to pay for it, and if OpenAI is able to advance convenience through these actions, they'll make billions.
You see negativity, I see disappointment that OpenAI isn’t trying to innovate, and instead hoping they can replay Google Search’s history for themselves
You just discovered the (capitalist) idea of growth... Any management of a big corp not going for the seemingly endless growth idea is going to be fired by their shareholders pretty quick.
It's a fairly obvious way for them to make money, as people are using it as a replacement for search engines, and that's how search engines have made money.
Who? Those of us who were paying attention to how tech companies have operated for the past 25 years.
They start out subsidized by investors and then once they have enough users and can no longer pay for them with the invested cash, they push more and more ads onto users.
And it was easy to see that LLMs are an especially devious place the inject ads because they can flow right into the the response and not even look like an ad, but rather feel like a casual recommendation.
It is literally a highway at this point for any B2C tech product. All the info they are collecting surely can be used for very targeted ads. Not hard to predict at all.
It could be more that those hanging around on wedding planning forums aren't really representative of the younger generation. If it's a wish of the couple, they should clearly communicate this on the invitation.
There are lots of young people who have some conception and respect of privacy and there are people who haven't. That's not a generational thing.. It's just that those without awareness of boundaries have now all the tech that screams in their face to stream everything to the world without consent. I can assure you that still lots of young folks are annoyed by those people.
Agree. I went to a family gathering recently, and my wife's cousin was walking around live streaming. People were pissed once they figured out that private conversations were uploading live to the internet.
The same guy did similar when his mom was on her death bed. Jesus Christ.
That's a good recipe for getting a black eye. The mother-to-be tends to be pretty much confined to her immediate affairs, but the partner…
(I'm sure everyone is different, but I've been there as the father-to-be, and I would have made a good effort of turning that live-stream into a live-colonoscopy.)
>The same guy did similar when his mom was on her death bed. Jesus Christ.
I am so sorry for your loss and I am out of words. Just, I just want to be with ya in silence for a while. I am sorry that you had to go through this. I am really speechless
I was definitely feeling something as I didn't think of the stranger's wife's cousin's mother? as dying but rather the stranger's wife dying and that cousin recording it.
But even now, yes you may have proved your point but death is so fucking weird and not talked about and sometimes I just get speechless, like someone just left the earth, let that sink in...
Honestly, I can somewhat both understand why he was live streaming now wanting more comments/everyone's final messages to go to her mother but at the same time, its definitely privacy invasive and might show their last moments and something of a behaviour I don't condone but I just don't know, now my opinion is mixed.
I didn't know the lady at all. I didn't even end up meeting the cousin, I heard about all this after the fact. My wife isn't broken up either - kind of distant family.
I get that for whistleblowers, journalists, investigators, ... I don't think it's relevant for a birthday party with children.
If it's me, I'm leaving the party. If it's my children attending, I'm strongly recommending them to leave the party (or just leave with them, depending on their age). Live-streaming a birthday party of children is obnoxious behavior that should not be tolerated.
This is the case where I find law in Europe better than USA. In germany you need consent to film or record other people.
The downside is the misuse of the law, what happens constantly, to basically prohibit (at least in practice) ANY recording activity. Is not unheard of, I have seen and experienced myself quite a few times, for example, a tourist being stopped and asked to delete a video of a simple recording in a park (police called immediately), because a random stupid person was around and wants to show how good he knows his rights… (see sister comment)
If it’s me, in Germany, I would instantly tell this person to stop filming and to delete any recordings. And if they streamed live to expect a letter from the (German equivalent of the) DA soon, as I would - as soon as back home - I would press charges and search damages.
Because in German publishing images/recordings of an individual without consent violates basic constitutional rights. And that’s nothing to f** with.
If minors were involved you’d be in a whole different can of soup even.
So while I don’t advocate for violence - as others have hinted in this thread - a black eye could actually be the lesser negative outcome for such a person.
And most states also allow you to leave a bar thirty seconds after your friend you arranged to meet there arrives, it would still be considered rude to do so and probably you wouldn’t be welcome in the future if you kept doing it.
Under US federal law one-party consent requires that you actually be a party to the conversation. This is why most security cameras do not record audio.
If you're wandering around livestreaming and picking up conversations you're not a participant in, it's a violation of federal wiretapping laws.
I watched multiple videos from Portland ICE protest, multiple videos of ICE arresting people, all with audio. Half the people at protests are recording.
If you were right all that would be illegal.
The magic word is: "reasonable expectation of privacy".
If you're in public, like in streets, in the mall etc. you don't have reasonable expectation of privacy. You can be recorded, with audio, and it's legal.
The two party consent rules only apply to private conduct e.g. you have a phone conversation. In states with two party consent the other person can't record the conversation without notifying you.
What you describe as "US federal law" sound more like anti-wiretapping law i.e. I can't plant a bug in your house and record your conversations. Which is duh, but not relevant to being recorded while in public.
I figured that "reasonable expectation of privacy" was a given in the scenario. It's a family gathering, the livestreamer is not being obvious about their recording, there's a "reasonable expectation of privacy".
Your ICE protest example is performed in public, its a protest, its not meant to be private, thus fails the test of "reasonable expectation of privacy". Action taken by agents of the state are also public actions, this has been tried many times in court.
Two-party consent is not federal law and varies state-by-state. But again it requires that you actually be a party to consent.
And yes by "US Federal Law" I am referencing the anti-wiretapping laws which prohibit, among other things, interception of oral communication via electronic means unless at least one party consents.
I'm not so sure that the family gathering scenario is well-defined, though. If I'm at a gathering in someone's house, and I'm in a room with only the person/people that I'm actively talking to, then I feel reasonably private in the sense that my words are falling only on the ears of intended recipients. But if I'm in a room with the people I'm talking to and also people I'm not talking to, then I acknowledge that ears beyond those involved in the conversation can catch wind of what I'm saying, which roughly equates to the absense of expectations of privacy.
It's important to remember that you're making this up. You're just sort of spontaneously interpreting "reasonable expectation of privacy" off the top of your head.
It's usually simpler than that: if you see them recording you, and if they aren't trespassing (i.e. breaking the law otherwise); or you are on their property or on public property that they are legally permitted to use, which carries a posted sign telling you that you may be recorded, you don't have a reasonable expectation of privacy. Otherwise you do.*
Somebody could possibly hear something has nothing to do with it. Consenting to being heard is not consenting to being recorded. But maintaining your presence in a place where people are allowed to record is. If it's your party, tell them to put it away or leave. If it's their party, you leave. If you are recording surreptitiously and you are not working with law enforcement, it's probably not going to be admissible in court and if you publish it, you're going to get sued. Depending on your state and local laws, you are likely to lose badly.
-----
[*] All of this depending specifically on how the term is defined in your state and local laws. For example, video has often been separated from audio for pragmatic reasons; security cameras are meant to record physical acts, not conversations. For a second example, many states have decided that sending your voice over a wire to a designated recipient as an electronic signal is already consenting for the person receiving that signal to be able to record it and use it as they please; others have not. For a rationale in the second case, imagine that you didn't have the right to reveal a letter that was sent to you.
If everyone is inside a private home, the host has not given permission to stream, and the streamer is deliberately keeping the camera/phone hidden, then no-one has waived their expectation of privacy, and the streamer is intercepting a conversation they are not a party to
> If you're in public, like in streets, in the mall etc. you don't have reasonable expectation of privacy. You can be recorded, with audio, and it's legal.
Just a note because I myself made the same argument very loudly 1-3 weeks ago...and was informed some states have different laws than I expected. Massachusetts, in particular.
(Note that MA limits clandestine recording, not the obvious recording in TFA blog about airsoft -- and it has been neither upheld nor overturned by SCOTUS)
>>> Massachusetts makes it a crime to secretly record a conversation, whether the conversation is in-person or taking place by telephone or another medium. See Mass. Gen. Laws ch. 272, § 99. Accordingly, if you are operating in Massachusetts, you should always inform all parties to a telephone call or conversation that you are recording, unless it is absolutely clear to everyone involved that you are recording (i.e., the recording is not "secret"). Under Massachusetts's wiretapping law, if a party to a conversation is aware that you are recording and does not want to be recorded, it is up to that person to leave the conversation.
>>> This law applies to secret video recording when sound is captured. In a 2007 case, a political activist was convicted of violating the wiretapping statute by secretly recording video of a Boston University police sergeant during a political protest in 2006. The activist was shooting footage of the protest when police ordered him to stop and then arrested him for continuing to operate the camera while hiding it in his coat. As part of the sentencing, the court ordered the defendant to remove the footage from the Internet. From this case, it appears that you can violate the statute by secretly recording, even when you are in a public place.
Wiretapping laws are set by states, and different states have different criteria. For example, the two-party consent in MA involves 'intercepting' the conversation so even listening on a microphone and not recording it is considered wiretapping, but not all states use that criteria. Some people, like public officials performing their duty in public-- e.g. cops and politicians-- can't have any expectation of privacy.
Presumably, a person holding up a phone live-streaming would be party to the conversation.
If two people are talking at a party, and a third person obviously comes by within earshot, then the two people can either stop talking, or they can continue, but the third person is now party to the conversation.
I've met thousands of developers over my career and i could put them into two categories: those who don't give a shit about intermediate commit messages (majority) and those who browse every single intermediate commit message in a PR (very few). To be honest, the latter had some tendency to be difficult to work with. It was also a useful discriminator to avoid getting those into my teams.
I tend to read intermediate commits because it can be helpful in understanding how the engineer thought through developing the feature. This is especially informative when reviewing more junior/mid-level code, or when a feature grows beyond what I would consider acceptable scope - obviously, avoiding these kinds of branches is the ideal state, and unfortunately the realty doesn’t let me always push back for smaller PRs.
This sounds unattainable to me. For code bases in the 2 million or more lines range, something as simple as refactoring the name of a poorly named base class can hit 5000 lines. It also was not a mistake with the original name it had, but you'd still like to change it to make it more readable given the evolution of the codebase. You would not split that up into multiple commits because that would be a mess and it would not compile unless done in one commit.
Such PR's shouldn't be the norm but the exception. What happens way more often is that such refactoring happen in addition to other criteria on the same PR. In high-functioning teams i've worked this is usually done as a separate PR / change, as they are aware of the complexity this operation adds by mixing it with scope-related changes and that refactoring shouldn't be in the scope of the original change.
There is the issue of just how visible truffles are from space though, if they grow under cover. That said, it may still work because you can find habitats that are very likely to have truffles. We've had some promising results looking at fungal biomass.
If there is a single advice i would give the young folks here: Don't listen to VC's. Live your life. Startup founder is more comparable to an olympic athlete in terms of what you have to give up to get there - by definition 99% of people who try no matter how brilliant won't walk this path successfully - but both will lose many things on this way without being much happier than before. This is also where most of this community is being very dishonest be it co-founder search or success stories: Only a very small percentage of people is mentally suited (e.g. extreme resilience) to go on with this gamble yet we encourage everyone to try it out here.
This. I'd also add that, in general, you don't need a large sum of money in the early stages, as long as your basic needs are covered. For instance, living with your parents for a while can be a smart move. More importantly, use time wisely: with discipline you can do or validate a lot over several quarters. By contrast, if you take the VC route, the metronome ticks much faster, often in a way that can be counterproductive for your startup. As unintuitive as it sounds.
reply