Nothing will ever be enough, for all interpretations of the statement, reveling in all the irony, pathos, and prideful triumph that could possibly be extracted from such interpretations from here to eternity
Contradictory anecdote: there’s basically only one way to write Elm, as it is a very trend-resistant language with minimal updates over long timespans, but most agents in my experience will throw Haskell syntax and Prelude functions into their Elm output. Compiler or LSP will often set them right but they still try it initially
I think you touch on a language feature I think is very important: compile time errors over runtime ones.
I'm biased, I preferred it this way before AI. But even so I think there is real merit. Firm guardrails and clear feedback seem to benefit AI.
Anecdotally, the worst AI performance I've seen was with gdscript, which is basically python minus the huge corpus of training data. Best results I'm getting with rust, which is in the opposite end of the strictness spectrum.
I do agentic Elm development every day (it's my job). I feel like what you describe was a problem with models perhaps two years ago. Today's models don't seem to struggle with it at all and in fact do seem to benefit from what the author describes.
I have worked extending the Elm compiler and both Opus 4.6, GPT 5.4 and GLM 5 had no issues both with the Elm compiler (written in Haskell) and my extended Elm.
I didn't see them hallucinate much, not more than on mainstream languages.
I’ve just started a new app with an Elm frontend. I’m using Grok Build, and it integrates really well.
The compiler is incredibly helpful because it catches errors and gives clear explanations and the LLM can iterate over it. I’ve also added the elm-review package with the default configuration, which is fantastic for ensuring code quality.
Despite the title, the article sure makes it seem like it’s the private company that runs the state’s warehouse’s fault; at least that’s who most of the interviewed retailers blame
Or you could spare the five minutes to watch the credits, seeing the names of all those people who made the movie you just enjoyed. Discuss the film during that time so you don’t spoil people in the library. Make some new friends.
It’s very rare that I maximize an application. I’m always stacking. However, I don’t think it’s an optimizing assumption: I am frequently fighting with the window manager as I rearrange my windows and it automatically maximizes them because I got too close to an edge of the screen
In general my browser is dead center or slightly to the right so I can access my other windows (terminal, throw away text editor, etc) easily where command tab is insufficient (when I have multiple terminal windows, eg)
> I am frequently fighting with the window manager as I rearrange my windows and it automatically maximizes them because I got too close to an edge of the screen
Strange, I constantly get annoyed by how slow and unresponsive the Mac's tiling is when dragging windows to the edge. At the top it has at least half a second delay for no reason. But at least the newest version now has caught up with Windows 7.
Presumably, since the first citation in the paper is said epidemiologist (Monteiro), this is the framework they rely on.
Unless you’re intent on scientific gatekeeping, in which case having actually read the reported study (it’s linked in the article fyi) would have offered much more effective methods of rebuttal than semantic quibbles.
It's not gatekeeping to point out that multiple studies have shown that Nova is a perfect example of "no one agrees on what processed foods are". Even when given Nova criteria, nutritionists repeatedly, across studies, fail to agree on categorization.
Nova also does not even attempt to categorize in terms of health because "processed" has nothing to do with "healthy" despite being used in conversations about public health. Absolutely perfect example of how bad the term "processed" is.
I would expect that the mode is a feature of the vs code integration and not something the model would necessarily even be aware of. For it to not operate correctly in the ask mode when it is properly set seems to me a bug in the underlying integration. The fact that the model responded the way it did and then corrected it is interesting.
Well, you didn’t share the exact text of the original prompt but you described yourself as having asked it to do something. These models are being trained for agentic behavior on data where an agent is asked _to do something_, and as their output is purely probabilistic, the rewarded response will then often include the text “I have done something” even though they have not done something. Perhaps there _is_ an issue with the integration that caused your experienced response, but purely based on my experience and the limited information you gave, my immediate guess is that the model positively associates your prompt with the generated response
Okay, let’s talk about that first command: sort all files in this directory by relevance. Relevance to what? Is this a permanent sort (what does it do to the file names?) or just a reordered ls output? What button in what OS is this superseding? Is this really an huge improvement over the smart search functionality in most OSes (besides requiring an open terminal and additional keystrokes for the abstractions)?
Some of these are slick despite not really being examples of the obsolescence of UX idioms. But that first one is a very strange example to lead with.
The video shows her driving away from the officers. They approach her window, she backs up a bit, turns her tires away from the officers and starts driving forward when the agent fires into the car
Incorrect. At least two of the 3 shots went through the driver's side window. She was driving by Jonathan Ross who shot at her head and then called her a "fcking btch"
She was doing exactly that. She was turning to leave. They escalated and then shot her. It's just blatant state murder. Governments killing people. Indefensible even by the thirstiest bootlickers
Humans will keep inventing and remixing
reply