|
| ▲ | chasd00 2 hours ago | parent | next [-] |
| Just give the LLM requirements and have it output rust. Just like giving a compiler a text file and it outputs machine code. |
| |
| ▲ | win311fwg 17 minutes ago | parent [-] | | Theoretically the LLMs could go straight to machine code. No need for any intermediate language. However, the HN stories have made it clear that LLMs are not great at going directly to machine code or Rust. Rust is, time and time again, only being used as an optimization intermediary. If LLMs were better to target it directly they wouldn't be always be stories about translating to it from another language. |
|
|
| ▲ | Gigachad 2 hours ago | parent | prev | next [-] |
| From the OP post it costs tens of thousands of dollars to do that compile. |
| |
| ▲ | rpozarickij 2 hours ago | parent [-] | | Given the rate of progress, it's hard to argue why this couldn't be a reality. If in the future Taalas-type chips with baked in frontier models are commonplace, this should be quite different price-wise from what we have now. It's a bit dizzying to imagine that LLMs might even be able operate at speeds of chatjimmy.ai, but we already have working tech that does exactly this (albeit with less intelligence/capabilities). |
|
|
| ▲ | pjmlp 5 hours ago | parent | prev [-] |
| Not really, the future are natural languages, with some markdown files for formal specification, yaml or whatever, and then Assembly gets generated directly. 3 GLs are going to slowly fade out as LLM tooling improves, and coding looks increasingly as envisioned by 4 GLs advocates. |
| |
| ▲ | NewLogic 4 hours ago | parent [-] | | Sounds awful, natural language sucks for describing complex problems and relationships. That's why people have historically reached for diagrams and pseudo code. | | |
|
