MantisShrimp90

My take is that this is largely right. To be specific though, I feel the future is natural language commands that will be translated into a proper language through llm systems.

In this way, the generated output, whether used as a proper program or just some scripts to do small activities, they can be audited later, reused, and tested even if a client created the request in plain language.

We would then mostly be translating bugs from english to the underlying language and bugs would mostly be people speaking ambiguously or just misspeaking

This is misunderstanding the problem really. People don't hate ai posters because they are bad, they are technically better than many normal posters. They hate ai posters because they hate ai generated work and desire to just be done with the whole thing.

By that logic they hate this even more because now its harder to tell its ai. This is really a person hating the means but using the ends to justify it rather than stating so outright

Many souls games define the opposite of this the traditional model is that an invader can attack aided by the enemies which is more dynamic but less of a pure test of skill. To get around this players made fight clubs where they let people invade them in a neutral area with no enemies, the players agree to do an honorable duel which goes against the nature of the mechanic but emphasizes skill of the individual.

That corporate systems are broken and it takes constant, unappreciated effort to make anything of worth because people who see and highlight real issues are labeled as "pessimists" and even includes specific steps to live in this toxic environment.

I think technically sound its just that the frontier models are just sooo in the news that al the money is around intelligence and big breaks in intelligence.

Once the economics change and we see less bit model deployments there will be much more work optimizing models at the pareto front.

Also yes people need to be able to sustainably run these things to start running a business. Building a business on the model pricing today is as smart as building a retirement plan on a gambling schedule

Its a good point that gets to the real heart of the issue. How do we handle when a model has no legitimate way to reach its goal? Do we ask them to stop and inform the user? Or have them push through those ethical bounds? We all say we want the first, but this exact same dynamic is what causes humans to cheat, arbitrary goals that don't care how you achieve them and just like humans I'm sure trainers are so happy with good results they overlook how it got there.

Half of me agrees with you. As someone who used to tinker with neovim all day I've had to learn just because you can program the problem doesn't mean you should and stick to a relatively minimal config.

Still, its a valid design choice with different design decisions compared to sway. But that's the point you get to choose.

Hyprland is much more "build your workspace with legos" so having a full lang like lua makes sense to properly integrate the various pieces.

I believe perfection is a dirty word because it has a pernicious effect on the human mind.

Striving towards perfection too often leads to yes over-engineering but I think more importantly it also: leads to way too much bike shedding due to the need to be perfect and allot of even emotional baggage when we don't make that perfect things.

Even the author admits that their definition of perfect can only arise with stringent requirements and I'll take it a step further, maybe it was perfect for that problem at that time but guess what change happens all the time, and as architects we have to think about future problems as much as current ones. With that in mind I think that having something that is good in many scenarios is better than the thing that is perfect in the scenario you start in.

Yea by having claude code in a terminal window within neovim rather than tmux you can leverage neovim commands to traverse, copy, paste and otherwise interact with the terminal window like any other buffer.

There are also plugins with more specific workflows but I like really seeing how much vanilla neovim can get done

Knowing and leveraging the editor deeply is the best high level advice. Sessions for persistence, windows and buffers to manage screen real-estate (including terminals), and the terminal command itself to run the agentic workflow of your choice.

I will concede that this is the primary gap in the ecosystem right now is PERSISTENT terminal buffers but the act of doing terminal work in neovim is straight up nice if you use neovim motions to leverage that relationship.

Terminals resuming in a session is just a feature to be added not a complete functional rewrite.

(Neo)vim is setup wonderfully for this era. Im with Justin on the take that neovim can replace tmux soon literally all that is left is being able to restart terminal sessions on restart (which is even set as a goal for summer of code).

Neovim can already have all the agents running in different terminal buffers or there are plugins popping up every day to have deep integrations with your favorite or we even have some interesting harnesses that are unique to neovim like sidekick.

As always, the ability to compose small tools and edit any file allow neovim to stay relevant and more powerful than ever in my opinion while not forcing workflow changes like the others

I mean others are saying its divided and that's true.

I guess the other side of your argument is... Is it better though? One could easily argue much of software development is promising projects strangled by their own technical debt and short sighted designs. It still has yet to be seen if AI can make well architected systems unsupervised. And this really was one of the few places where technical people shared their labors of love and appreciated the technical skills of a community.

Also, all the externalities whether that be environmental, social, or even technical and hn is really bad at actually talking about these things directly so we have to couch it all as the tool being bad. That's the part you're missing for many its more like its not good enough to justify the costs

I mean yea my take is that there's basically nothing that claude could benefit from that humans wont. So I see no reason to make claude-specific docs.

With that said, yes, the difference is I KNOW claude will read my docs, especially if I shove it into the context and therefore, I KNOW I'm getting ROI on that work.

As someone who has written docs for years I have spent too many hours writing docs that my colleagues proceed to just ignore and ask me to explain verbally. Its a culture thing if people don't have a natural instinct to read docs and a culture of documentation and asking others to read the docs INSTEAD of bothering the human.

Also, there may be something to the theory that people don't learn well from docs as tutorial. I find 10x faster return when I make a video for people or tutor them through something rather than sending them a link and asking them to read it. Often this is because good docs are disciplined and try to answer the one question they were asked. Which is great, untill you realize most are missing necessary background so now you're in a bind. Do you document foundations that are covered in other places? Or do you cover them in your own words making 10x more work for questionable value? Its not an easy question