Vegenoid
Vegenoid on Hacker News
We have determined that the initial conditions of the universe and the laws of physics are at fault for this incident.
Sounds great! Let’s see the code.
To understand if writing is good for a certain domain or purpose, you really do need to at least be decent at writing for that purpose.
If it’s just about aesthetics or how it makes you feel, then yes I agree because how it made you feel is a signal of whether it’s good. Code is not like this, code is about accomplishing a specific function.
You just described the exact same scenario that I’ve heard over and over for the last 2 years. “I didn’t think AI would take over software engineering. But recently, it blew me away with a greenfield implementation of something that already exists and that I know how to make. It has few users and has spent little time in the wild. Now I’m a believer.”
It’s definitely getting better, but this isn’t the kind of thing that is going to change the world. It needs to be good at things that are much more entangled with the world for that.
People say this, and it sounds reasonable. But, as a user of software, I certainly am not feeling a lot of software getting more reliable and higher quality. Mostly I feel the opposite of that.
I like the idea, but we already have the terminal bell. In my setup, when an agent is done or needs something, it emits a bell. Based on config, this results in a desktop notification if I’m not in the terminal, or a toast from my multiplexer if I’m in the terminal. The terminal pane gets a colored “bell” icon in its title that is cleared when I attach to it.
The total lack of mention of the terminal bell in the article is weird. I think it needs to be addressed for the protocol to be taken seriously. More granular info sounds nice, but also nice is the simplicity of the bell.
It still takes decent hardware to run local LLMs that are at all useful. What would be really cool is if we could get useful LLMs on hardware cheap enough to go into “things”.
1. There are no rules of economics. Economists attempt to understand things that happen and use that understanding to predict future events, but frankly there’s not a lot of consensus.
2. Economics is a function of human behavior, not horse behavior. Economics is about coordinating human effort. Humans make economics, horses don’t. When economics change in a way that is bad for horses, the horses have no recourse. When economics change in a way that is bad for humans, the affected humans seek to change things.
One of the key points of the comment you replied to is that you don’t need a very powerful model to do MCP stuff, such as local Qwen. The “let the agent figure it out” approach works much better with powerful models, such as Claude (which you mentioned you are using).
Yes, and now we are full circle: what is (allegedly) bananas is that using VSCode’s remote edit feature has the potentially surprising and unintuitive behavior of installing a VSCode agent on the target machine.
My absolute greatest skill in my career, that has consistently set me apart from my peers, is that I read documentation thoroughly.
It is shocking how much of a differentiator this is. You will discover that the software you’re already using is much more capable than you realized.
…which we attempt to constrain by encouraging the use of tools that make it harder to fuck shit up.
Spotify, the comment I replied to drew a comparison from Shopify to Spotify.
I think I’ll start a company called Shpoptify.
Spotify has progressively gotten much worse over the last 15 years, all while the size of their engineering team has ballooned.
I am very unsurprised by this outcome.
People wonder why good software becomes bad, and it’s because the people who were good at engineering are often outmaneuvered by corporate-politics savvy people in a growing company. One of the best political moves in a company is to have a lot of people under you.
A couple years ago, an engineer I know who has always been a very poor performer and lacks initiative, but is friendly and non-confrontational, was hired by GitHub. It would not have been hard for GitHub to find a much better engineer, but this person would be an easy person to keep under a manager on a team who wouldn’t leave or make waves. That can be more important to some managers than skills.
The difference is that Minecraft gives you much more granular access to manipulate the world, which enables a lot people to feel more connected to the world and become more invested in it.
Agree with the thrust of your comment, but I had to comment on this:
> In a full banana republic, technical compliance with the law will not prevent consequences for failing to do what the authorities want. In a jurisdiction with perfect rule of law, it always will.
I think you may be misunderstanding that many laws, even in fair, just societies, are intentionally designed to be flexible. The real world is so variable and messy that in many cases it isn't feasible for a law to be written such it can be unambiguously determined whether or not a specific action violated the law. Laws often rely on humans using context to judge whether something violates the spirit of a law, and in a just society, this is a good thing.
My point is that I don't believe the idea of "perfect rule of law" is sensible. Law is always necessarily a bit fuzzy and nebulous.
Using a corporation's free offerings
isn't freeloading. Microsoft
wants people to put their code on GitHub. They want GitHub to be
the place where source code is hosted, it is incredibly valuable. Saying "GitHub is sucking and I might leave" is information that Microsoft wants to know if they want to preserve GitHub's dominance.
Of course some people take it too far. Of course there are reasons that the outages are occurring. But Microsoft wants GitHub to be a core, reliable pillar of the software world. Nobody's making them do that, they do it because it's good for them.
I don't understand how you can read a thesis that predicts AGI in 2027 (and the subsequent explosion to ASI) and say that it "all ended up becoming true in 2026".
"My vibecoded stuff is indistinguishable from handwritten stuff" and "I got anti-AI comments after vibecoding my website even though I didn't say anything about AI" are not very compatible with each other.
Taking the lack of ability to identify good AI fiction as evidence that there is good AI fiction is absurd, because it means that there is no evidence which could ever point to there not being good AI fiction. There must be evidence which could contradict a hypothesis for it to be sensible.
If a job is well-paying, there will always be many people going into it for the money. High paying and only people who love it do it are pretty much incompatible.
I do not understand why people who get serious about it want so badly for it to be called table tennis. Ping pong is a way more fun name, and table tennis just seems to make it out to be a smaller, inferior version of tennis.
I think people get distracted by the "percentage of revenue paid to musicians" thing, when the bigger reason streaming pays out so little to artists is that people pay $10-$15 per month for unlimited access to all music. Even 80% of that, split across dozens or hundreds of musicians, is not very much. Of course, it's also worth remembering that streaming was partially a response to widespread piracy. It's difficult to get people to pay very much at scale for easily copied digital media.
In addition, a greater share of the payout (relative to number of streams) goes to big music distributors that control the biggest, most popular artists and have the leverage and employees to negotiate those agreements.
> They are indicted in federal court… what kind of mindless ideologue thinks this was just a whim for giggles?
It is well-known that the bar for securing an indictment is very low. There is a famous quote about it: "Any good prosecutor can get a grand jury to indict a ham sandwich."
It too is well-known that the Trump administration is exerting great pressure on the DOJ to charge political opponents with crimes. The most public of these was when the DOJ twice failed to secure an indictment against Letitia James, following pressure from Trump and the firing of DOJ prosecutors who resisted pursuing the case against James. This was notable because indictments are so easy to get.
The current acting Attorney General, Todd Blanche, was asked about a message Trump sent to the previous AG (Bondi), where Trump wrote ""What about Comey, Adam 'Shifty' Schiff, Leticia??? ... They impeached me twice, and indicted me (5 times!), OVER NOTHING. JUSTICE MUST BE SERVED, NOW!!!". Blanche stated ""That type of communication from President Trump should make every American happy".
The SPLC has been highly critical of Trump for years, and been a legal thorn in his side. It's always been the case that a case being brought shouldn't be taken as any implication of guilt, and it is especially true in this case. The evidence, or lack thereof, will be revealed in court in due time.
Good to know, thanks for reporting back
This would require LLMs being good at knowing when they are doing a bad job, which they are still terrible at. With a good testing and verification harness set up, sure, then it could just go to a more powerful model if it can't make tests pass. But not a lot of usage is like this.
Unfortunately I do not know, I haven’t done anything to configure this as far as I am aware. I am on macOS.
AFAICT Backblaze
does back up .git directories. I have many repos backed up. The .git directory is hidden by default in the web UI (along with all other hidden files), but there is an option to show them.
You should try downloading one of your backed up git repos to see if it actually does contain the full history, I just checked several and everything looks good.
Yes, I agree with you, I think that regulation is needed here and that this was a dumb thing to say. I'm just saying that my reaction to Zuckerberg saying that people must love his product if they use it a lot is exactly what I'd expect him to say. It's also exactly why other parties must step in.