The peak was in 2014, far before any coherent AI became a thing.
As someone with substantial "points" accumulated all a full decade ago, I can easily see why. If you only allow certain opinions and criteria for specific subjects, your user will eventually shrink to only the few that possessed them.
It's a Spartan death. Don't blame it on the Persians or Athens.
I use a mixture of claude code and codex and kiro as my swarm.
They communicate through my own harness, and it's working pretty well so far. claude code is being overtaken by codex however because I noticed lately the accuracy of the latter is the best.
As someone who is on the other side, the amount of familiar, LLM generated reports are overwhelming and usually falls under "not familiar with product design/security scope" category. But there are also really good ones - so I can't afford to not take actual look at each, but it gets tiring and we need a solution. Spamming the former category with LLM generated "rationale" isn't that solution (yes I can tell this article is mostly LLM generated).
Unfortunately, this looks like the former case. If the software can execute arbitrary code/binary, and you place a malicious binary, that's up to you to secure/sandbox the workspace, not the software. Unless cursor commit themselves to securing the user environment, which I don't think they are in the business of.
If you are generating a CVE report with LLM, please use LLM responsibly in helping you reproduce deterministically. Then please do the write up yourself, keep it as concise as possible and strip most adjectives in any LLM generated sections as they cannot help themselves to write without mostly useless exaggerations.
I am sort of a no UI (except browser) user for a very long time now, and vim is still incredibly useful.
Granted, the language servers are getting dusted, but it's much nicer to write goals in markdown in vim and send it to LLM in a self-written harness CLI; and even look at the results in the same way. All unix. LLM is just the latest toolbox addition.
But why should apple invest in developing their own models? Why would it be correct?
Or phrase it in a very similar ask, why don't they invest in power plants? The model space is truly crowded, what do they gain or recover suppose they are SOTA? Across the Pacific they are pumping out free models that are only 6-12 months behind. What business sense does it make for Apple to develop their own models?
If you end up with 2 to 3 times more code. That is HORRIBLE, because it means about 50-66% of the code is otherwise unnecessary. Those are eventually going to become unmaintainable garbage.
However, if you get 2 to 3 times the code in the interim, that's probably less than what's needed. I find myself cycle through almost 10x-20x amount of code implementations to get what I want which is actually less code, simple solution and desired behavior.
Given a specific behavior, there are usually just 1 simplest implementation, whether done by human or AI. However, there are 100 ways to do it with more complexity and either handwritten or AI slop, it will mean pain down the line. We used to have a lot of handwritten complexity because of certain design pattern culture, but they used to be contained because the ability to generate them is costly. Now it's much more risky and therefore more important to have simplicity as the guiding principle in ALL projects.
The issue with these kind of porting is edge case bugs - far smaller project/physic simulation has hit the same thing especially when original code isn't exactly clean, or sometimes only worked because of a logic bug.
This means you can play for maybe 10 minutes on the happy path but just as you are getting into the zone either a CTD or some strange event would make the game/simulation unplayable.
And while debugging is made easier, it's much more effort than telling the model to convert the code. Hence it's usually not done in these demos.
This article is rated 100% on my AI smell meter, making it less trustworthy despite convincing arguments.
For instance, I'm now really only sure that author measured a 2000 ppm CO2 in a meeting room once. Everything else could just be LLM trying to invent convincing argument.
> When I walk into my office and sit at my desk, I’m choosing to be there. When I walk away, I have a door I can close, and a life outside the room that the digital world is no longer allowed to reach.
Being intentional is hard, and a little friction helping it is welcome. But I do hope for myself that I can be intentional in everything that I do (this includes having fun, being with family, and even doomscrolling).
That's a natural result of introducing LLM to current standard software development without modifying the rest of it (the part that doesn't involve creating code).
I think at the end of this we'll have a new software engineering paradigm.
Mostly nobody now worry about binaries or instructions because those are for the compilers, even undefined behavior are mostly ignored.
You can either tailor the development pattern for LLM, or have LLM come write for the same old development pattern. I think there is going to be a difference.
That would only works until it doesn't. The suppliers got supplier too and those in turn have their own supplier. I don't know about any specific contract but I bet there's a force majeure or price excluding input cost somewhere.
While I appreciate the positivity, but I've honestly grown to appreciate grammar mistakes. Just like it's not X, it's Y indicated AI, those indicated that the effort behind was human.
Honestly, no need to write 4000 words if the story can be told in 400. The story is what matters, not word count or "flow".
That commit count alone should not become any problem for infrastructure, even for Azure. They probably developed some ungodly mess with actions that did not/could not translate very well on Azure infrastructure.