Even the iOS and macOS typing correction engine has been getting worse for me over the past few OS updates. I’m now typing this on iOS, and it’s really annoying how it injects completely unrelated words, replaces minor typos with completely irrelevant words. Same in Safari on macOS. The previous release felt better than now, but still worse than a couple years ago.
Spellcheck is an absolutely perfect example of what happens with technology long-term. Once the hype cycle is over for a certain tech, it gets left to languish, slowly degrading until it's completely useless. We should be far more outraged at how poor basic things like this still are in 2025. They are embarrassingly bad.
Yeah it finishes my sentences and goes back and replaces entire words with other words that are not even in the same category of noun, then replaces pronouns and conjunctions to completely make up a new sentence for me in something I've already typed. I'm not stupid and I meant what I typed. If I didn't mean what I typed I would have typed something else. Which I didn't.
Until the model injects a subtle change to your logic that does type-check and then goes haywire in production. Just takes a colleague of yours under pressure and another one to review the PR, and then you’re on call and they out sick or on vacation.
I haven’t used Cursor yet. Some colleagues have and seemed happy. I’ve had GitHub Copilot on for what feels like a couple years, a few days ago VS Code was extended to provide an agentic workflow, MCP, bring-your-own-key, it interprets instructions in a codebase. But the UX and the outputs are bad in over 3/4 of cases. It’s a nuisance to me. It injects bad code even though it has the full context. Is Cursor genuinely any better?
To me it feels like people that benefit from or at least enjoy that sort of assistance and I solve vastly different problems and code very differently.
I’ve done exhausting code reviews on juniors’ and middles’ PRs but what I’ve been feeling lately is that I’m reviewing changes introduced by a very naive poster. It doesn’t even type-check. Regardless of whether it’s Claude 3.7, o1, o3-mini, or a few models from Hugging Face.
I don’t understand how people find that useful. Yesterday I literally wasted half an hour for a test suite setup a colleague of mine introduced to the codebase that wasn’t good, and I tried delegating that fix to several of the Copilot models. All of them missed the point, some even introduced security vulnerabilities in the process invalidating JWT validation, I tried “vide coding” it till it works, until I gave up in frustration and just used an ordinary search engine, which led me to the docs, in which I immediately found the right knob. I reverted all that crap and did the simple and correct thing. So my conclusion was simple: vibe coding and LLMs made the codebase unnecessarily more complicated and wasted my time. How on earth do people code whole apps with that?
I think it works until it doesn't. The nature of technical debt of this kind means you can sort of coast on things until the complexity of the system reaches such a level that it's effectively painted into a corner, and nothing but a massive teardown will do as a fix.
A Markov chain is commonly understood to be a time-discrete Markov process. Intuitively, it’s a “chain” because you can “single out” its states in time rather than intervals. That’s also Markov’s original definition. Instead of Wassermann one can look up the notion in Wikipedia. A path is a notion relevant to the state space of a process - it’s a realization of states at every single point in time for the time span of interest.
Hard no. I’ve had that in lots of cases, it just applied some symmetry pattern to come up with purposefully absent public endpoints that exist for employees only. It gets dangerous the moment you put as much trust in it as you’re suggesting.
The pace differs though. A junior would need a week for a feature an LLM can produce in an hour. And you’re expected to validate that just as quickly. And LLMs are trained to appeal to the reader, unlike an average junior dev. Devs will only get lazy the more they rely on LLMs. It’s like you’re at the university and there’s no homework anymore, just lectures. You’re just passively ingesting data, not getting trained on real problems because you’ve got AI to do that for you. So you’re no longer challenged to grow anymore in your ___domain. What’s left are hard problems that the AI will mislead you on because it’s unfamiliar with them, and your opportunity to learn was lost to delegating to AI. In the end the pressure will grow at work, more features will be expected in shorter time frames. You’ll get even less time to learn and grow as a developer or engineer.
I hear you. But consider this: substitute “LLM” in what you said above with “coworker” or “direct report”.
Does having a coworker automatically make a person dumb and no longer willing or able to grow? Does an engineer who becomes a manager instantly lose their ability to work or grow or learn? Sometimes, yes I know, but it’s not a foregone conclusion.
Agents are a new tool in our arsenal and we get to choose how we use them and what it will do for us, and what it will do to us, each as individuals.
You can substitute anything like “banana” or “parrot” for that and ask the same question.
Change of roles is a twist I didn’t suggest, it’s not related to my argument. I was talking about an engineering role. I’m not seeing an analogy with what you’re suggesting. Even less so does your suggested “immediately” resonate with me. Such transitions are rarely is immediate. Growth on an alternative career path is a different story.
The problem that I see here is that we’re not given that choice you’re considering. Take for example the recent Shopify pivot. It is now expected by the management because they believe the exaggerated hype, especially motivated during the ongoing financing crunch - in many places. So it’s not a lawnmower we’re talking about here but an oracle one would need to be capable of challenging.
I can’t speak to how others apply the LLMs, but in my coding experience they’re mostly in the way. A couple days ago VSCode released an agentic workflow similar to Cursor’s. And I must say, the YouTube demo was persuasive and I thought I’d just have to move to VSCode off JetBrains IDEs.
So I gave it a spin, and after the past couple days, it’s been the most terrible IDE experience so far. The LLMs are always in the way, I’ve got Claude 3.5, 3.7, o1, o3-mini, o4, Gemini 2.0-flash, 2.5-pro, with/without reasoning, own models. Embedded Copilot is bugged, editor/agentic Copilot is bugged - it breaks your code if you selectively reject suggestions, your file buffer gets mangled, need to revert everything completely even if something was useful. Sidebar chat can get just as confusing as before. Typescript, Python, Java, Kotlin, Go. Rust won’t even compile, and don’t get me started on C++ codebases. Never had it type-check with mypy and pylance.
In many cases even with codebases, extra MCP servers and fetching remote docs, it’s just not up to the task of making code even type check. Sometimes it just times out or fails on network errors. Very fragile, unreliable, misleading.
I don’t know what people vibe code, but for a variety of codebases I’ve had to work on, it’s just in the way, injecting nonsense or outright garbage, which I need to reject every time. It’s useful as a sed alternative, but a less reliable one, a regex is often faster than 3+ prompts and waiting. It breaks my flow of conscience, I lose creativity and need to check everything after it. Dunning-Kruger maybe.
To me that workflow is but a tailored and integrated StackOverflow, with snippets adapted to your code. Not sure how productive it is to let snippet insertions interfere with your flow, but very helpful when you forget or stumble.
The more people rely on it, the more surprise awaits around the corner the moment AI fails. Now devs rely more on the network link instead of their brain, just like when people used to vibe code using StackOverflow. Creativity is at the stake. It must be kept in tone to stay productive.
There’s a lot of work that’s a waste of time. If the goal is to replace devs, such companies will lose money in the end. If the goal is to assist devs and make them more productive, the LLMs need to adapt to take over such tasks reliably, e.g., scaffolding, standard algorithms, “best practices,” simulating and questioning design/architecture, and the UX must improve.
I feel like most discussions touching on Rust revolve around the same lines - one person says they don’t want to use Rust (for whatever reason), a proponent starts regurgitating the selling points, the former feels misunderstood (because that all has been heard many times before), the latter snubs at taking the former as being stubborn.
I’ve been through my Rust hype phase, and I’ve been through thoughtfully applying it for web services and a greenfield messaging broker, albeit nothing systems level. With a decade or so C++ behind the belt, I don’t feel an app team is necessarily more productive over the lifecycle of the project if they pick Rust over C++, much less so if they pick it over Java.
I’ve been doing mostly low-latency JVM projects. I can extract better performance from a JVM and a given infrastructure than from Rust. Ease of development and the option to delegate the lifetimes to the GC, or just get a huge heap, is often the escape hatch you need to make through the tight deadline.
In Rust, you need just one “smart” colleague to make the project unmaintainable - wasting everyone’s time on optimizing the type signatures making it thereby impenetrable to anyone outside the team, or easy to forget the derivation a few months later on.
There was a nice suggestion on HN somewhere to distinguish between an area beneficial particularly to Rust (slow pace, settled architecture, more low-level) as opposed to the area with fewer fruits to reap for Rust where other semantics prevails.
Good points, the JVM is absolutely underrated these days imo and Rust won't always be a strictly better choice especially for established teams. From what I see though a lot of this repetitive back-and-forth starts with somebody saying that they personally prefer Rust or simply describing its advantages over other languages from their perspective, and every time there's backlash from people responding as if the author were trying to personally force them into using Rust in their own projects.
I think it's great that you can build solid projects efficiently in C++ or Java! People should be free to choose whatever works best for them; as someone who does love Rust I'm of course happy to see it gaining traction, but if the flavor of the month were to suddenly change I don't think I'd feel the need to go out of my way trying to tear the new thing down.
And particularly often while you’re typing, hitting the spacebar or return to confirm whatever pops up, only to make you perplexed and try to recollect those few milliseconds you believe to have managed to see the name to try to find out what you’ve just been made to approve or decline.
