This comment is extremely prejudicial[1]. Not only is language a part of people's heritage and culture, which in itself provides value, but also what you've said is incredibly biased and also simply incorrect. For example, both Mandarin and Spanish have more first-language speakers than English[2]. Almost 40 languages have over 50 million speakers, each.

1. https://en.wikipedia.org/wiki/Linguistic_discrimination 2. https://en.wikipedia.org/wiki/List_of_languages_by_total_num...

And yeah, the lack of collective political will sucks. It would be naïve, however, to think that there is no value in ensuring longevity in our current and future infrastructure. And improving it to sustain the population giving these companies their value is an obvious win.

I agree, some of the problems are more difficult. I don't think that's the case for all of them. And, besides, these companies could be demonstrating how to approach problems and where their users could spend tokens to help with these problems.

Should not these companies try to work on these problems _because_ they are difficult?

I'm sure they must do some of this type of work, right?

Why would I do that? Well, I wanted to understand more deeply how differences in my prompting might impact the outcomes of the model. I also wanted to get generally better at writing prompts. And of course, improving at controlling context and seeing how models can go off the rails. Just by being better at understanding these patterns, I feel more confident in general at when and how to use LLMs in my daily work.

I think, in general, understanding not only that earlier models are weaker, but also _how_ they are weaker, is useful in its own right. It gives you an extra tool to use.

I will say, the biggest findings for "weaknesses" I've found are in training data. If you're keeping your libraries up-to-date, and you're using newer methods or functionality from those libraries, AI will constantly fail to identify with those new things. For example, Zod v4 came out recently and the older models absolutely fail to understand that it uses some different syntax and methods under the hood. Jest now supports `using` syntax for its spyOn method, and models just can't figure it out. Even with system prompts and telling them directly, the existing training data is just too overpowering.

I'll admit to being a "one prompt to rule them all" developer, and will not let a chat go longer than the first input I give. If mistakes are made, I fix the system prompt or the input prompt and try again. And I make sure the work is broken down as much as possible. That means taking the time to do some discovery before I hit send.

Is anyone else using many smaller specific agents? What types of patterns are you employing? TIA

1. https://github.com/humanlayer/advanced-context-engineering-f...

And what about users like this, whose comment are very much entirely LLM generated and possibly even a bot? https://news.ycombinator.com/threads?id=BelVisgarra