Would having a dedicated programming language specifically for LLMs be a viable

<!-- SC_OFF --><div class="md"><p>I asked gpt about this, and it said yes, and gave some good examples of how some python code might look like in a new language, where the

<!-- SC_OFF --><div class="md"><p>If LLMs are gonna write most of our code anyway, why are we still making them write Python/Java/Rust?</p> <p>Why not make a language specifically

<!-- SC_OFF --><div class="md"><p>Are there any solutions where a large language model isn’t trained on data in specific languages—such as English, Spanish, French, etc.—but is

<!-- SC_OFF --><div class="md"><p>I've been using STT models and noticed there are specific models for things like English. I've wondered why we haven't had the equivalent for

<!-- SC_OFF --><div class="md"><p>Every &quot;AI agent&quot; that controls a computer today does this: generate text → parse it → execute → serialize result back to text → repeat.

<!-- SC_OFF --><div class="md"><p>The news about Ulysses Sequence Parallelism enabling million-token contexts is fascinating for local LLMs. While the potential for deeper context

<!-- SC_OFF --><div class="md"><p>I asked Gemini to give me all the days that have &quot;d&quot; in them. It returned -</p> <p>Monday, Wednesday, Thursday, Sunday<br />

<a href="https://news.ycombinator.com/item?id=48771515">Comments</a>