schrodinger
But.
Something's lost in this need for perfection, knowing that every bug will be found quickly and cheaply if not fixed. It tilts the time spent towards security hardening rather than feature development — which I still agree is a _net_ good.
An analogy I find keen is going from living in a safe neighborhood where nothing happens if you forget to lock your back patio before bed, to one where if you ever once forget to lock your back patio, it will be instantly noticed — either by something benevolent, or something malicious¹.
I know this is indisputably "better." But something's lost and something's gained in living every day², and in this case what's lost the ability to be innocent and naive on the Internet with a low likelihood of repercussions. To be clear, there's always a baseline need to be careful, don't leave port 443 open etc, but you could run a simple webserver you wrote up as a toy project without too much concern.
Will the trend towards every gap being found nearly immediately result in better software, a safer world, and overall happier people? I don't think so.
-- ¹I saw this analogy somewhere on Hacker News recently, so I don't want to steal credit. I'll update if I come across it.
²Joni Mitchell, "Both Sides Now" (1966). Highly recommend a listen.
Even if you disclose to the buyer that it's counterfeit, it's _still_ illegal. You can't just use someone else's name, logo, or protected designs without authorization.
In fact, it's so severe, you can face >= 10 yrs in Federal PMIA prison and owe fines up to $2M — just for the first offense.
Honestly, I initially regretted posting my comment because besides a native iPhone app, I've never built GUI software. I did no research of my one and asked a very open-ended question and felt intellectually dishonest and lazy, and almost deleted it.
I'm so glad I didn't.
This comment is one of the most information-dense helpful resources I've read in a long time (and such a welcome reprieve from the "slop"), that anything I did to contribute to its existence was worth it.
Thank you so much for writing this, and I strongly recommend you post this somewhere very public — on your _beautiful_ personal site at the very least, and I'll do my best to spread it around. I've only built an exquisitely designed iPhone app, as the sole eng alongside a great designer, and barely considered anything but native because our brand was very high-end in the startup-of-a-lifetime great way, and we wouldn't settle for anything else.
But especially with Agentic AI, I could imagine some scenarios where being able to run the guts of your editor out of process, e.g. on a cloud box or even a local docker container, being pretty advantageous.
This is how Claude Code GUI works but to be fair that’s less of an editor.
Pardon the snark, but they literally wrote an article about giving up on code reviews because they push 35k _commits_, not even lines of code (I’m assuming — they say “changes,” which I’d assume are commits), and we’re bottlenecked on reviews.
Instead, they claim to just review the _intent_ of the PR and presume correctness will be caught by more AI.
Seems insane to me, but hey, what do I know. I suppose you could argue with bugs so easily fixable now, it’s not worth spending the traditional cost of prevention. I just can’t imagine what that many changes could be doing...
Source: https://www.anthropic.com/engineering/redesigning-source-con... (presumably also written by an AI)
If I were to build an editor, I’d want the GUI platform-native so would probably go straight for Xcode and Swift.
If I had a strong aversion to Swift, I might consider a hybrid design where the UI is Swift and write a backend in a modern, fast language I prefer (Go/Rust/C# come to mind, but this isn’t a call-to-arms in the language wars). I believe this could be achieved since LSP works well as a backend server supplying IDE-level niceties, so I could keep most functionality implementations there. I’d have to have a strong reason though since Swift is a fine language, and AI does much of the writing now.
Then again, most devs live on a Mac and deploy to Linux, and are increasingly using Agents which may be better off cloud-hosted or at least sandboxed, so lightweight Swift UI and most logic in a headless cli app could be an interesting design choice.
But the important part to me would be low-bloat and native UI, and I’ve never found cross-platform UI frameworks to hold up in practice — even if only because different OSes necessarily have different ideas of idiomatic design, so you’d either be using least common denominator UI components that feel uncanny, or reimplementing the UI for each platform.
Have you found a language / framework combo that’s fast, fits into the OS well, and is _fun_ to write and use? Or is your idea that separate implementations are now so low cost — who cares — let the AI maintain them?
Legitimately asking in good faith, so please don’t interpret anything as snippy in there — it’s just my understanding of the state of the world. I’d genuinely love to learn about how cross-platform options have expanded if I’m missing something!
Instead, you could make it so anyone who answers after the first person starts out muted and hears a message like: "Uncle Bob's on the line, press 1 to join the call or stay on the line to listen quietly." They could then choose whether or not to join in.
Just a thought! Great idea nonetheless — I'd buy it if I had a valid use case!
Great idea nonetheless though!
* Actionable
* Constructive
* Succinct
* Borne out of relevant experience
And you were sure to thank them for the contribution. This is a model HN comment.
Who cares?
FWIW I use my free iCloud email account with my custom domain since Apple (unlike Google) offers that as a free service. However, I just forward all email to my GMail address and use a custom reply-to in GMail so it _seems_ like I'm using the custom domain in both directions.
Yes, you could ask an LLM to choose between 4 options, and sure have it include a confidence score. But at the end of the day it's still LLM-ing and outputting tokens based on the total probability of the chain of tokens that precedes it to figure out what's most likely to come next.
This taps into a lower level of the model, skipping that tedious token generation step, and exposes you to more raw output from the model, e.g. the actual probabilities involved in answering the question.
It still needs to "think like an LLM" to interpret the question, so it's in the same family, but the thought process gets short-circuited once the question is understood and the raw weights are then extracted as pure, weighted probabilities.
Why would you want to use it? What does it enable beyond a traditional LLM?
(a) It's much more efficient (read: cheaper and faster), and not by a %, but an order of magnitude or two. This makes it practical to be used when an LLM isn't, due to its speed and accuracy, which opens up new use cases.
(b) By getting the raw options and weights, you're not getting the LLM's "spin" on the output, nor hallucination risk — instead, you're using an MRI to pull out exactly what it's thinking before the bullshit verbalization engine kicks in.
Does that help? Please correct me if I'm wrong or went too far in simplifying it, but that's my high-level understanding. I hope this helps.
(4) could be a precursor to a sales pitch for a paid service and (6) obviously has malevolent purposes. But the rest... just people testing agents? Causing mischief?
In other words, the rich don't generally break the law to avoid paying taxes. Rather, they find _legal_ loopholes that work for them, and even create them through lobbying.
Which suggests that legal measures _would_ be likely to work!
On that note, there’s another rule about not commenting on comment votes as well:
>>> Please don't comment about the voting on comments. It never does any good, and it makes boring reading.
https://news.ycombinator.com/newsguidelines.html
FWIW I agree with you, but the rules do seem mostly effective in general.
Anyways, welcome to HN!
Shouldn't someone be looking at some monitoring and see "phillyunsolvedmurders.com," think "hmm that doesn't sound right," and look into it?
I'd actually expect them to engage with, say, 1k websites to voluntarily participate for some remuneration and then restrict the Agents' access to those domains, but apparently I'm crazy.
I’m not taking a side on that debate, just clarifying the relevancy of that quote.
Whereas for an LLM, it's just a way to ~waste~ spend tokens.
Unless you think the future doesn't need mathematicians, we ought to respect their requests.
I'm not confident in that statement, but I think it's well within the realm of possibility. Then again, so is needing humans to architect / steer for another 2 decades. We live in exciting times!
Writing code is _hard_ because it's by definition accurate logic math will tons of abstractions that build on each other. Our brains are great at this. Frontier models with lotsa context are too. Let's ignore those though.
There are a lot of problems that are simple. Accuracy is important (e.g. is it nudity?), but it's still simple. The difference between Jev and the general idea of small models you described is that Jev (and a million copycats, Jev being a copycat itself) only answers multiple choice. That's clever; why wax poetic when you can ask a question and just get back the multiple choice, standardized tests love them for a reason.
So really it's: a) "Big Know it All" Models. Slow and pricey, but they'll handle anything you through at them. b) "Small Domain-Specific" model that still speak answers. They need some amount of "can form eloquent answers" in there with the specialized knowledge so still have a bit of a floor, but totally make sense. c) "Memorized multiple choice tests, and can read but not write." Sometimes open-ended answers really are a downside when the answer space is sufficiently constrained, and read-side literacy really
Not nit-picking, but (c) really is more different than just a specialized model. And you're right, lots of problems fit that shape — hell, before AI blue up the world that's _all_ computers could do — and many times ambiguity and hallucinations are drawbacks of open-ended answers. You just need to ensure that "N/A" is always a valid answer, or at least that you get a confidence score.
Imagine there's a very advanced crossword club where anybody can join and take a stab at these crosswords for the love of solving puzzles. Many of them are so difficult that no one's been able to solve them yet, but we know they're all solvable.
One day, someone comes along with a super advanced crossword solver application, and it makes easy work of these crosswords. They run it on a few to prove how powerful it is, and then the community says, "Oh wow, that's cool, but please don't run it on any more of our advanced crosswords because they're very hard for us to come up with, and we really enjoy solving them by hand."
That's really what this compares to. I wouldn't call that gatekeeping; just respect. Respect for the game, respect for people's desire to have these hard problems to continue to work on, solving by hand.
If the company with the super advanced crossword solver then continues to use it and publish the results, they're effectively stealing the crosswords from this community. Soon, all the puzzles will be solved, leaving nothing left for the community to work on for fun.
That doesn't sound like gatekeeping to me. That just sounds like someone asking "Please be respectful and leave the remaining puzzles for us to solve by hand.” A simple plea not to be an asshole.
This is why anonymity is necessary for true freedom and privacy. If data _can_ be traced and connected, it will be. This aligns with a 1995 Supreme Court opinion (McIntyre v. Ohio Elections Commission), where Justice John Paul Stevens wrote that "anonymity is a shield from the tyranny of the majority," noting that it "exemplifies the purpose behind the Bill of Rights, and of the First Amendment in particular: to protect unpopular individuals from retaliation... at the hand of an intolerant society."
Umm, I played plenty of GTA growing up and I’ve never stolen a car. People are actually very good at separating fantasy from reality, believe it or not.