The definition is at https://x.com/karpathy/status/1886192184808149383 and no that does not match what is in the branch. Systemically migrating a code base using an LLM does not match the defintion of vibe coding.
> I’m seeing people apply the term “vibe coding” to all forms of code written with the assistance of AI. I think that both dilutes the term and gives a false impression of what’s possible with responsible AI-assisted programming.
Then "vibe coding" is a useless term, if it just means "LLM-assisted coding". We might as well just say "LLM-assisted coding" or "AI coding" or whatever.
As much as I find the word "vibe" generally annoying (in all contexts), I actually really like "vibe coding" as "LLM did everything and I didn't even look at it". It's a succinct, useful way to describe that mode of doing things. Diluting it down to "LLM-assisted coding" makes it useless.
Nah, I'm not big on these "it either matches the way ___ used it or it's useless" binaries. The term is the term, it's recent, and people are using various forms of the others you mentioned. People use it loosely, people use it specifically, this is the way for many colloquial terms, and definitions form around them and expand over time or change.
It sort of surprises me how uptight people are getting about a term that was mentioned on X last year and has since been tossed around to loosely imply that a machine did between zero and all of the work. Just because it doesn't match exactly does not mean it's useless, it maps to a concept, if the details are important and ambiguous, then elaborate.
All language is "coined terms". The point is that if you dilute the definition of a term, you make the term useless. Evolution of a term isn't done automatically. Correcting terms such as these pushed the evolution in a more useful way. Also, evolution of language is not a magic spell that automatically forgives people on making language mistakes.
I don’t think it was made clear: the questions were about the code op “wrote” but they used a llm so couldn’t remember any of it. Probably got there from a git blame. This happens.
It sucks how everything feels like a toy. I think meshtastic is the closest thing to a “product”. They made a bunch of bad architectural decisions that are haunting them now like how nodes broadcast its info.
It doesn't surprise me. This is a deep networking problem and very few CS people know anything about networking or how to design clean, fast, low-overhead network protocols and systems.
If IP were designed today the packets would have 500+ bytes of plain text JSON as headers and the spec would support hundreds of extensions.
It's a fundamentally really hard problem that looks easy on the surface. There is no solution that works well beyond the small scale. Many people have tried. It's the same kind of thing that draws people to try to write IPv8.
Because they are toys. For real work it makes so much more sense to use the internet. With the new satellite tech you can reach the internet everywhere.
Mesh radio is a fun way to chat with radio nerds in your area. Not a serious infrastructure.
So what’s the real solution for when Starlink is too expensive and too high power? I really want to solution for remote mountaineering communication that’s not just GMRS. And what about remote weather sensors? I really don’t need a full internet connection just to send a tiny payload every 5 minutes.
Meshtastic should be the obvious answer for this but in my limited experience the app(s) and code are buggy on even the most typical hardware. Wish it wasn’t the case but it is.
If you're talking about a few miles/KMs between nodes, plain old LoRaWAN might be more than sufficient, esp. for the sensor use case. The nice thing about using LoRaWAN is that's it's literally providing an IPv6 overlay so you can run e.g. MQTT or a text-based messaging protocol designed for regular TCP/IP use. UDP is preferable to avoid frequent session resets and keepalive traffic chewing up your available bandwidth.
Meshtastic and MeshCore can theoretically provide "infinite" range so long as there are peers between the nodes you want to connect. Theoretically, mobile peers can also serve as store-and-forward nodes so that reachability doesn't need to be constant, just frequent enough to handle the messaging you want to do.
I would absolutely not rely on either for a safety-critical application, though. If you want emergency comms in case something happens while you're out on the mountain, use a satellite communicator. There are a ton of these marketed for outdoor/portable use, and they have much more robust "SOS" capabilities (up to and including direct dispatch of search-and-rescue).
LoRaWAN seems interesting but the documentation and availability of is either "Crypto hobby project from Seedstudio" or "Strange telecom companies selling $900 base stations that still expect an internet connection (for licensing?)". Maybe I'm missing something but the LoRaWAN doesn't see to sell itself very well when half the vendors are behind "Contact for quote" pages.
Of course, for real emergencies I have a Garmin SOS device. It would just be "nice" to have something for local 2-5 km communication that doesn't need a clear view of sky, works partially underground, etc. GMRS is "fine" but from a physics perspective a digital signal with Chirp encoding should go further and be more reliable.
Seems like JS8Call or Packet radio might more in line with what I want. It's just surprising that something like Meshtastic hasn't replaced them.
> Of course, for real emergencies I have a Garmin SOS device.
that's why the mesh radio/LoRaWAN-type ecosystems suck. I don't mean to be rude or snarky; just to point out a very contextually-relevant example against your argument.
For the average consumer who needs this functionality seriously, there's a proprietary (and often costly) solution. Subtract those mission-critical-remote-comms devices and you're left with hobbyist needs, so you get hobbyist-quality ecosystems.
Meshtastic supports store and forward for ESP32 nodes that have a few MB of RAM, but not for the nRF52 devices that can't practically buffer much. I've only used the latter class of devices, so I don't have any experience with how well Meshtastic's store and forward works in practice.
Depends what exactly it is you want. But phones these days can communicate with satellites for emergency messaging.
I think people need to think more about what the actual scenario they have in mind is because it seems most people think of mesh radio as some backup for the government shutting the internet down. When in reality it’s almost useless for that since it’s so easy to jam or flood mesh radio.
We may see a day when the internet is not available, or when interacting with it represents an unacceptable risk. It's a good idea to know how to set up your own.
It's a different jamming scenario however. Starlink is comparatively centralised, and reliant on both terrestrial (ground stations) and satellite communication. While the terminals themselves are sparse and widely distributed, the backbone infrastructure is far less so. It's possible to target the satellites, ground stations and critical service dependencies (e.g. GPS) rather than needing to target the hundred of thousands/millions of terminals directly.
The mesh networks are dealing with, by definition, a sparse and widely distributed set of devices which are independently configured and controlled, and in their current widely available form are only dealing with terrestrial communication. Without that point of centralisation you would need to focus on targetted regional jamming, as from a practical standpoint you cannot perform wideband RF jamming over an entire country - signal jammers don't scale that well, and geographic features come into play. As an example you might effectively block mesh networks from operating reliably in a given city, but if people were to move outside of that area then the mesh would operate again.
Geography is both a strength and a weakness here: a mountain range will impede direct communication with someone on the other side, but it will also have the same effect on jammers which will vastly increase the cost to deploy them in a ubiquitous fashion.
I suspect jamming LoRa could be a lot easier than most radio though. LoRa signals are incredibly weak and long range. A jammer which jams at a massively higher power level could cover a massive area. You can also just flood the network with messages that nodes will happily relay further for you.
That's a DoS attack, not "jamming". RF jamming usually relies on flooding frequencies with garbage which doesn't get interpreted as valid protocol traffic but does "crowd out" legitimate use.
The protocol-aware class of attack you describe does require some knowledge of the radio parameters being used, since LoRa runs on very narrow bands and uses both time and frequency-hopping to avoid congestion on any one virtual channel. They even apply (very basic) encryption to messages to prevent unknown senders from flooding the channel.
Unfortunately, both systems come preconfigured out of the box to use a default configuration which most users never override. So like cheap FRS/GMRS walkie talkies, all it takes is a few jerks who don't care about common use to overwhelm everyone with bogus messages. If you fire up a new device running the default Meshtastic firmware in any kind of dense urban environment, odds are it will more or less immediately get inundated with spam: "ping", "test", "hello from <neighborhood>", etc.
And since MT + MC both flood the shared channels to push messages across intermediary nodes, they pretty much self-DDoS by doing...nothing.
Probably not short range connections. The application layer will have to change but we can still have an internet that operates when we pass each other on the street or share an elevator--the primary bandwidth carrier being devices being physically moved through space, and cross-device chatter being opportunistic.
Also, it might not be jamming. It might be that whoever is operating the satellites at the time denies access unless you enable inspection, and then sells that info to somebody who would hurt you--or whatever other can't-trust-the-middleman dystopia you care to imagine.
That’s really the killer for survivalist mesh ideas. It’s trivially easy to jam, and if it’s open it’s also easy to DDOS.
Jamming is done in military scenarios too, but in that case it’s limited by the fact that a jammer is a big transmitter painting itself with a big sign that says “fire missile here.” Civilian mesh doesn’t have that fallback.
Neglect is a bigger killer than active denial. If the Internet goes down it will likely be because a few execs decided to replace competent network admins with AI, or because all the competent network admins decided to quiet-quit because they aren't being paid jack compared to the folks hawking AI vaporware.
Battlestar Galactica opened my eyes to this problem more than electronic warfare in games of the day did. It's freaky (read: terrifying) that we're getting to a point that people are starting to take "embedded information (and decision)" systems serious enough to deploy them into meat space.
True. But look at the situation in Iran. As much as internet seems like an essential part of daily life, there is the possibility for the governments to shut it down.
I've been tinkering with the tech to make city-wide flrc meshes joined together over the internet, my estimates are that it should be at least able to support thousands of users per region.
This has been tried with mqtt bridges in Meshtastic. But it’s ultimately kind of pointless because if you are planning some kind of internet alternative, you don’t want to build something that falls over the moment the internet goes down.
That works with just basic mesh radio. The internet bridges thing is tempting but ultimately a bit useless and doesn't push people to extend the mesh natively.
Don't get me wrong, I like the mesh/* ideas around everyone being able to prop up a router/repeater, but I've seen what that can do in an urban environment... unfortunately for some, I don't plan on letting every tom dick and harry to set up their own towers.
And also them calling out Andy for they key? Stupid.
The official Android app (blessed by the "community") still has in-app purchases up. It gates the remote repeater management, afair one of the things Andy's MeshOS app for TDeck is gating.
The underlying protocol is open source, but the companion app isn't.
Yes, in the current version of Meshcore app it's possible to manage the repeater without the key, after a wait period, but that changed recently and they still nudge towards in-app purchase.
Similarly Andy's firmware* can be used for free, without purchasing a key, unless the user wants the full functionality.
*is it even his, considering it's been AI-generated?
A big mess. Also the network is a big mess, now I understand why.
What even is Warp now? I remember it as the electron terminal and totally dismissing it. Then I think I read it got the RIIR treatment, but there was already Ghostty and Alacritty by then. Now it looks like it’s another AI thing?
Warp was always an AI thing, as I recall - the seem much heavier on AI bandwagon nowadays, but their whole thing was a terminal for teams where you could share knowledge and command palettes and generate stuff.
Gotcha, I must have encountered them later on then - thanks for posting the receipts!
I was a happy user for a while, but eventually some bugs drove me back to iTerm2 (in my case, hanging forever after certain terraform commands finished). Ghostty has filled my need for a better terminal since then.
You should be able to just turn off the language server. Go to the lightning bolt icon in the bottom bar, "Stop all servers" or just the PHP one lighting up your source code.
I think it will be difficult to remove bias when you ask a model to compare alternative products. The model will simply lie, as with a biased human opinion and you will need to consult multiple models for a diversity of opinion and presumably use a "trusted" model to fuse the results. Anonymity will be a key tool in reducing the model's ability to engage in algorithmic pricing.
Writers have many options to deceive their audience without outright lying.
If a journalist is given an all-expenses-paid trip to an exotic location for the launch of a new product, and they review the product and say it's great - are they lying?
If a reviewer writes an article comparing certain types of product, but their review only includes products where affiliate links pay a 10% commission - are they lying?
If a journalist is vaguely aware of rumours about newsworthy, under-reported Event X but also that their publication has a big sponsorship deal with folks that Event X makes look bad, and they don't investigate the rumours or report on them - are they lying?
If a reviewer hears a claim from X, and they report the claim credulously, without adding the context that X has a history making false claims - are they lying?
I'm using bias to mean hidden motivations to the benefit of other parties. Feel free to substitute a better word.
EDIT: actually I'm really not sure what hairs we're trying to split here. I see bias as a departure from objectivity. It can be conscious or unconscious, but when someone is selling something, it's frequently conscious and self-serving, and I believe that's referred to as a lie.
> Blocking transparent ads is not a good idea. The consequence is that you will be fed opaque ads.
Doesn't history show us you just get both?
You pay to get into the movies, then they show you adverts before the film, then the film includes paid product placement of cars, computers, phones, food, etc.
You watch youtube ads, to see a video containing a sponsored ad read, where a guy is woodworking using branded tools he was given for free.
You search on Google for reviews and see search ads, on your way to a review article surrounded by ads, and the review is full of affiliate links.
I don't buy this premise. Nothing stops a company from trying to hide ads in the first place, and plenty of them do. Ad blockers for web content have been a thing for years, and using an ad blocker has continued to be strictly a better experience regardless of how many "organic" ads are present on a page.
By removing option 2, you only leave options 1 and 3.
If the product has costs (always true), then option 1 means that there is no gratis tier. So you force companies to remove their free tier, or to make ads opaque.
If you want to enjoy a free product without paying and without ads, then do so, but don't pretend you are an activist for doing so, just pay the ethical cost instead of trying to avoid paying that as well.
This isn't complex either, the only reason you don't get it is because you don't want to get it, you want things that are gratis without paying for them, and you want the free things to be given to you on your terms, and you don't want to be guilty about it. It's easier to think of yourself as righteous than to recognize that you want to be a leech.
You've been asked before to make your points without swipes. Please make the effort to observe the guidelines. The very reason this is a place people want to discuss things is that we have the guidelines and others make the effort to observe them.
> By removing option 2, you only leave options 1 and 3.
My point is that these are not exclusive options, and in practice, most companies will not feel constrained to only pick one of them.
> This isn't complex either, the only reason you don't get it is because you don't want to get it, you want things that are gratis without paying for them, and you want the free things to be given to you on your terms, and you don't want to be guilty about it. It's easier to think of yourself as righteous than to recognize that you want to be a leech.
No, I'm arguing that because companies in practice are going to use multiple of these when they can, my attempts to influence them by keeping the door open on 2 will not have any effect whatsoever, so I might as well close the door on it.
I think you're overestimating the marginal cost of doing one of them after you've already done the other. If a company has a bunch of ad-buying customers and a bunch of transparent ads, putting together some work to make a bunch of opaque ones for the exact same customers is not necessarily going to be that hard. I don't see how you can claim that it's mathematically guaranteed that the number of customers who decide that they'd pay more to have both is not enough to make that work turn a profit.
First that i should have said correlated rather than proportional.
Second that even if there's an inverse influence, there's also a positive influence between both forms of advertisement.
But in terms of proportion I still maintain that if you eliminate one type of advertisement the ratio will become 100% of the other, which is as undeniable as it is tautological.
Ah yes, the classic "my business plan is your moral problem; you owe me your eyes on my ads because I'm the idiot giving things away for free."
People don't want ads. You imply that "if you accept ads then things will be free" but they will not. Never accept ads. Not for a free service, certainly not in a paid product. Ads exist to enable leaching in both direction in exchange for what ends up being nearly mind control. But it is two-way leaching - companies benefit without the friction of explicit payment, consumers get a service without explicitly paying via money. The downside is neither can stop the bad-incentives motivating bad actions from the other side.
Ads are a deal with the devil, and rejecting them outright is allowed via that deal, just as companies can withdraw their free service. It cuts both ways.
Please don't sneer. My comment was about as mild an ask as we ever make. We won't be adjusting anything, and indeed we'd happily turn the rate limiter off if you just respect the guidelines. This is only a place where people want to participate because we have guidelines and people make the effort to observe them. There's no reason why you couldn't be one of them. We want this to be a place where the full range of positions and perspectives can be represented and discussed, but snark and contempt just drags the place down, regardless of anyone's ideology.
Your implication that "you will be fed" other ads if you block the main ones is unsubstantiated. But even if it was true, it does not matter. Because the so-called "opaque" ads can and in my opinion should be blocked as well.
I think that in general blocking all ads is always a good idea.
The reason is that there is no negative consequence in doing so. A person has absolutely no obligation, not even an implied one, to watch or otherwise consume any ad. I think that as long as there are ways to remove or block ads, people should use them.
That being said, if the companies wish to intertwine their products with ads that are indistinguishable from the actual content and therefore unblockable, it is okay. They have the right to do that if they want.
But, in the same fashion, the customers have every right to turn away from all such products. And never consider using them ever again.
>Because the so-called "opaque" ads can and in my opinion should be blocked as well
You can't, that's one of the main purposes. Instead of having ads marked and delimited, the are woven into the content, even if you could detect them (as a plugin or gratis moderator), removing them would potentially corrupt the product. It may be a part of a joke or the plot itself.
It's simpler to do one thing than to do two. You make a choice and you do that.
Could they be doing opaque ads right now and we wouldn't know? It's possible, that will probably eventually come to light and it might have legal consequences, but sure it's possible.
But it's not a given, and your logic of "it would make zero sense to leave money on the table" is certainly not a QED, it's absolute reductionism.
Totally. I’ll get by fine without ChatGPT, and I guarantee I can go without whatever crappy products the ad network you shill for partner with. In the meantime I’ll keep blocking evey ad I can.
In fact I’d be better off. It’s interesting that the most ad laden products are often the worst for you: YouTube, social media. Whereas the good uses of time: books, art, are ad free.
I'm a shill, not of any ad network, but of the idea of respecting contracts and law, even those we don't read and click on an "I agree" box.
Consider that stallman didn't encourage followers to pirate microsoft, he encouraged boycotting and made his own alternative software and contracts.
Sounds like a better way to go about it no? Why would you want to be a part of a club that doesn't want you as a member, and to the extent it does, it develops unmarked unskippable ads mixed with content so as to keep monetizing from adblocking users.
So yeah, I'm anti adblock but not pro ads, I don't do freemium or ads myself when selling, i do use free dependencies but donor based . I guess I'd be lawful neutral?who would have thunk there's more than 2 alignments!
Comparing to twitter is astute, as there are some analysis that point to it being mostly bots in 2025.
I can see the same happening for GitHub, in fact it seems to be actively trying to move in that direction: a platform for AI agents to host code, to review code, with little to no human activity.
Just like everyone who didn’t want to deal with bots left twitter, they will soon leave GitHub for similar reasons. I’m sure there is a future for GitHub as the code hosting platform for agents but it should be no surprise then when real people like Mitchell and the rest of us jump ship.
https://github.com/oven-sh/bun/compare/claude/phase-a-port
This single commit is 65k lines of additions
https://github.com/oven-sh/bun/commit/ffa6ce211a0267161ae48b...
reply