Show HN: GlyphLang – An AI-first programming language

출처: Hacker News — https://news.ycombinator.com/item?id=46571166

• GlyphLang의 특징
  • AI에 의해 생성되고 인간이 검토하는 방식으로 설계됨
  • 기존 언어보다 더 적은 토큰 사용
  • 코드 예시
    • Python: @app.route('/users/') def get_user(id): user = db.query("SELECT * FROM users WHERE id = ?", id) return jsonify(user)
    • GlyphLang: @ GET /users/:id { $ user = db.query("SELECT * FROM users WHERE id = ?", id) > user }
  • 사용 가능한 기능
    • 바이트코드 컴파일러, JIT, LSP, VS Code 확장, PostgreSQL, WebSockets, async/await, 제네릭
  • 문서 및 리포지토리 링크
    • Docs: glyphlang.dev/docs
    • GitHub: github.com/GlyphLang/GlyphLang

의견

댓글/토론에서 나온 의견을 참고용으로 정리했습니다. (사실로 단정하지 말고 맥락 확인 권장)

• Hacker News · @rubyn00bie: I think there’s a certain amount of novelty to this, and the aesthetic of the language I find pleasing, but I’m a little confused… Admittedly, I didn’t read the entire doc and only quickly glanced at the source… But is it just transpiling Golang code to and from this syntax, or is it intended to be a whole language ev…
  • 링크: https://news.ycombinator.com/item?id=46571540
• Hacker News · @goose0004: That's an awesome tool! I think textclip.sh solves a different problem though (correct me if I'm wrong - this is the first I've been exposed to it). Compression at the URL/transport layer helps with sharing prompts, but the token count still hits you once the text is decompressed and fed into the m…
  • 링크: https://news.ycombinator.com/item?id=46571533
• Hacker News · @noosphr: I've found that short symbols cause collisions with other tokens in the llms vocabulary. It is generally much better to have long descriptive names for everything in a language than short ones. An example that shocked me was using an xml translation of C for better vector search. The lack of curly braces made the…
  • 링크: https://news.ycombinator.com/item?id=46571458
• Hacker News · @rubyn00bie: Yeah, big plus one from me. I recently tried to investigate some sort of alternative encoding to/from “the prompt,” and was swiftly told that was both not possible and would work against me. As you pointed out, the LLMs are trained on language and language itself is often not terse. Trying to skirt that will caus…
  • 링크: https://news.ycombinator.com/item?id=46571613
• Hacker News · @jbritton: I had a conversation with Claude about what language to work in. It was a web app and it led me to Typescript mainly because of the training data for the model, plus typing and being able to write pure functions. Haskell might have been preferred except for the lower amounts of training data.
  • 링크: https://news.ycombinator.com/item?id=46571553
• Hacker News · @jaggederest: Funny, I've been noodling on something that goes the other direction - avoiding symbols as much as possible and trying to use full english words. Very underbaked but https://github.com/jaggederest/locque
  • 링크: https://news.ycombinator.com/item?id=46571734

댓글

댓글을 읽어오는 중입니다.