Personally I would never build my business on a technology tied to a specific vendor that makes it difficult to switch if said vendor delivers a poor service or massively raises the price.
When evaluating a third-party service like Cognito in this case or a mail provider, I either require that it uses an open standard for access like SMTP or the interface that I need to use is small enough that I can wrap it in my own layer of indirection so I can easily mock it and swap it out later. Most of the time I never switch it. But god damn, does it feel good to know that I can move if I need to and I'm not locked in.
It’s interesting how AI may both raise and lower the quality of software. It’s very easy to send an AI agent on an open-ended bug hunt, and if it wastes a bunch of time and effort and finds nothing, no big deal. Time is much more important for a human developer with a salary.
This is where I believe strong typing (like, Haskell-strong or stronger) and functional programming in general will be a win. The confidence I have that my fixes are localised when fixing Haskell code is infinitely stronger than fixing even Java, not speak about C, code.
Haskell's type system would not easily prevent this bug. It's not good at numeric/logic issues like that. When people say "Haskell makes it impossible to write bugs" they mean "Haskell has enums" (ADTs).
Liquid Haskell might require you to prove that the divisor is nonzero, but even in standard Haskell there's common idioms for ensuring that a list is non-empty (data NonEmpty a = a :| [a]) or that text is non-empty (newtype NonEmptyText = NonEmptyText Text, with non-exported constructor, helpers like make :: Text -> NonEmptyText, or more advanced tricks like https://exploring-better-ways.bellroy.com/haskell-koan-type-... ).
The big problem preventing this approach from working for numbers is that it's just so cumbersome there. Most of this is because all the arithmetic operators are bundled into a single Num typeclass, and `fromInteger :: Num a => Integer -> a` has a type that's impossible for a "non-zero number" wrapper to satisfy.
Definitely room for improvement on Haskell's standard library when it comes to the number-related type classes. Modern Haskell could do very well in this area with a good type-class redesign in this area. The issue I think is that this would invalidate a lot of existing code, relying upon that. But you can already replace Prelude with something else in your own code if you want to.
I meant the constrained types by hiding the constructors. Super annoying, not automatically convertible, in Haskell you have to remember what the fake constructor is called, and write it every time you use it, but at least it's efficiently implemented with newtype, unlike the Java OOP version. Think about writing a value with several nested constrained types, like NonEmptyListOne (makeNonZeroNumber 42, 'h' `NonEmptyString` "ello world"). It's just really annoying.
The blog link I mentioned avoids this cost with literals, by providing using a required type argument to check the string length at compile time without TH. It requires a relatively recent GHC:
make :: forall symbol -> (IsNonEmptySymbol symbol) => NonEmptyText
type family IsNonEmptySymbol symbol :: Constraint where
IsNonEmptySymbol "" = Unsatisfiable (Text "Expected a non-empty string")
IsNonEmptySymbol _ = (()::Constraint) -- empty constraint is always satisfied
I am not claiming you cant write buggy code in Haskell! But following good functional style, your bug will more likely be compartmentalised, and fixing it will not break some other part of your program.
Sure! I have done my fair share of pretending Java and C++ support my functional style. But at the end of the day, you have better support for writing that style in a real functional programming language. And I wonder how well one can enforce a functional style in say Java or C++ upon the LLMs. Who knows, they might be great at it?
People don’t say "Haskell makes it impossible to write bugs"! You may have heard "if it compiles it works" which is somewhat tongue in cheek, but also true for a sufficiently loose interpretation of "works" in a way it is not true for languages with a less strong and flexible type system.
You haven't mentioned the dynamic typed languages that I believe should die -- Python and Javascript. The only good use case for dynamic typing is notebooks (niche of R lang) where you're throwing out the code you just wrote after getting the result you wanted from it.
Imo, formal methods like more expressive/stricter type systems are key to making LLM generated code successful. Of course models will get better, but trusting the output will become much easier with a type system that proves more properties.
Dependent types is one possible direction. Not sure when a language with dependent types will arise which will be useful for making real programs.
Agda is the most mature dependently typed programming languae (having been around since the 90s – it is basically Haskell on steroids), but has a more proof-assistant flavor than an actual programming language flavor. Opus & Fable write Agda quite well, so LLMs can understand dependent types.
That hasn’t been that bad. My real issue has been the time sink involved in following along with the maintainer and jumper through their hoops. Even after I demonstrate a flaw and a potential fix. My schedule is just so busy I need to pencil in time to deal with them.
The missing part of this is that verifying the bug with LLMs is also easy, and so is adversarially reviewing the proposed fix with LLMs.
The only thing left for you to do should be directional decisions. The LLMs should pause and rope you in if the fix involves directional/invariant changes.
No one can keep up with the volume of code AI produces.
We wont stop using AI.
We will use AI to check AI.
Of course this is crazy, but it will also unlock pretty insane scaling and productivity and ultimately we will manage it on either end via requirements and tests.
> it will also unlock pretty insane scaling and productivity
Insane scaling of bloat, bugs, and technical debt I'd say.
> We will manage it on either end via requirements and tests
It is so crazy that this is being touted as a sane strategy. When I was a much worse programmer, I tried to write a big complicated string manipulation function to take two types of scripts in a language and add diacritics. I had the requirements very clear. I had the tests very clearly with all the edge cases. But I didn't have a good and clear picture of how to attack the problem which was quite novel for me. As I got closer to passing all the tests it got exponentially more unruly and confusing. And nearing the end I was frantically changing little bits here and there wincing and praying and hoping the tests would pass. "Please work! Come on!" Then when I got close enough, I could never ever think about touching that mess again.
I was a below average programmer then throwing myself at some novel problem I didn't understand. Throwing LLMs that produce below average code at novel problems and relying on tests and requirements is not where we want to go to make real progress.
(Years later after much learning and coding myself I was able to redo the function in a totally different way. This time I actually understood how to attack the strange problem and made something clean, clear, and robust that just worked. The tests then become a secondary guardrail, not the main force of correction.)
We are seeing such a massive regression from what we've learned over the years of CS.
>Insane scaling of bloat, bugs, and technical debt I'd say.
You just described every legacy codebase. Many of which are widely used and do a lot of sales. You dont need a clean codebase to have a valuable product.
>It is so crazy that this is being touted as a sane strategy.
Re-read what I said. I literally called it crazy.
It is the same dynamic that gave us customer service from some call center in India. Why would companies do this? Customer service got worse. Are they stupid? No, it's just worth it. The quality goes down but the business can scale more so it doesnt matter.
AI will absolutely be good enough at doing things that we'll happily accept some jankiness at times so that we can devote an extra 3000 hours per year per person to other things.
Im not even suggesting its a good thing. I just think the incentive structure dictates it. You're not going to have time to maintain a small slice of some service by hand.
You can point AI at any AI produced code and ask it to review it, get back 10 bullet points and a few pages of prose. And the fun part is, you can do that over and over and over again!
This happens all the time. Yesterday, I ran into an especially egregious case.
I had Fable add a new subcommand to our internal CLI tool. I reviewed and tested it locally and had to suggest several fixes that I feel like I wouldn't have had to tell a human senior engineer to do. When it finally submitted the PR, I had it on a loop waiting a few minutes for comments on the PR, then assessing/addressing/replying-to/resolving them, and then repeating again until all AI reviewers were okay with it. It ended up going through dozens of revisions and ended up with 160 comments left on the PR.
You're suggesting that LLMs get better at fixing bugs/vulnerabilities, but at the same time stop getting better at finding them? What if this difference is inherent and essential?
Absolutely not. By most accounts they're terrible at fixing anything other than trivial bugs in complex codebases e.g. Linux kernel, but they're much better at finding them.
Manual testing, and making sure that the AI didn't create so many bugs.
But, to the underlying question, obviously as we automate more and more of our work, of course we provide less and less value. We're heading towards a future where selling thought for money isn't going to work so well.
In fairness at root this has been going on for awhile. No one can keep up with the volume of machine code that modern more abstracted codebases produce.
We didn't stop using syntactic programming languages we used code to check code.
Not sure it's really crazy at all. It's been an abstraction for programmers probably since we stopped soldering transistors to each other.
In my experience, there are two ways to use AI: speed or quality. Speed is where you give the AI a task to do and you review it; quality is where you write the code yourself and you get AI to review it. Both are valid for different situations.
Generate multiple solutions- they do not to work 100% correctly.
And than I check which I would prefer. Which is more to our applications taste.
And than I would take the vibe output as a kind of a ‚plan‘ which I use to implement but not follow 100% and at the end I take my solution and review it.
I gain speed with that because I often can quickly see the pros and cons of a solution way better than when I would manually do it and hang on a major roadblock and also I even see such roadblocks in the vibe output - it’s mostly the part with an unnecessary amount of new code that looks nonsensical.
I had the same knee-jerk reaction. "Did I read that correctly?"
But yeah, I guess it can be used to increase certain aspects of quality by letting them go wild. But I think I mostly hear about security or crash issues. In my experience they don't outweigh the number of other issues they cause. Like UI bugs. I've seen more than one service constantly rolling out features that are completely broken, just to have a completely new, still broken, solution available the next day.
I don't care if you call it an over-engineered looping machine or what, there are concrete benefits to using LLMs for this. They work faster than developing your own looping algorithm and more often produce useful results than not.
It's not even like fuzzers are valuable because of the process they use specifically either; the value is that they produce a concrete input that you can use as a reproducible test case at that point. The value could be produced by gazing into a crystal ball for all I care, as long as I can use what it gives me to reproduce a bug.
I dislike AI, but if AI finds real bugs then this is in my opinion objectively a positive thing. Of course the question is what constitutes a real bug.
From a security perspective, panic at runtime is not that bad for security. Much better than continuing to run with undefined behavior. If someone sends a malformed video in and it crashes the ffmpeg process you can just log it and restart it. Vs potentially exploiting the system.
The social media companies remove these kinds of videos after the fact but do nothing about the algorithm that encourages people to post more and more outrageous content. I honestly feel social media is a net-negative for society and I’m really hoping an AI slop avalanche kills it for good.
Some doctors absolutely would abuse this. I used to date someone whose sister was an endodontist and there was another endodontist in the building who was making over $1m a year. She ended up seeing one of that endodontist’s patients and realized that the other doctor had been making all that money by giving people medical procedures they absolutely did not need.
But only another medical professional would know that; the patients were completely oblivious. I said she should blow the whistle but she “didn’t want to rock the boat”. It definitely changed how I feel about doctors. There’s a massive level of trust there, which most doctors will honor but a few will exploit.
Citation very much needed. Society today is full of people in power who exploit others. Cops, ceos, spouses, etc. Very rarely are they "made an example of", and when they are it doesn't seem to change the intuitions.
This article is AI slop but it does illustrate a good point: if articles need to be written on how to do something as simple as exiting the app, it’s poorly designed. They’ve had a very long time to make exiting vim more user-friendly.
I found Udemy useful to learn new languages and technologies. I like it because it’s a whole course that builds on the previous lessons, not just a single tutorial that makes assumptions about what you might know or not know.
Is it really necessary to build AI data centers so frantically that it causes massive debt and inflation? They could do it slower and the sky wouldn’t fall.
I’m honestly amazed that Ray-Ban put their reputation at stake for this partnership. People will find increasingly ingenious ways to disable the recording LED and so everyone will become suspicious of ALL Ray-Bans.
what? They're not some social ethnic group. When I think of Raybans, I think of there being probably 1 person who makes 90% of the actual decisions. Its a nametag. It's probably ultimately owned by the same org that owns all the other eye wear brands.
The uncomfortable truth is that a decent proportion of the internet’s blog content was probably created solely for SEO purposes. But at least someone wrote it and put some degree of effort into it. Now you can just create content lazily and not need to care. I met someone recently who was starting a new business and they were creating loads of AI-written articles for their blog that they didn’t even bother proof-reading because someone had told them that was important for Google ranking.
reply