zlacker

[parent] [thread] 5 comments
1. lallys+(OP)[view] [source] 2025-05-07 11:54:27
The software tool takes a higher-level input to produce the executable.

I'm waiting for LLMs to integrate directly into programming languages.

The discussions sound a bit like the early days of when compilers started coming out, and people had been using direct assembler before. And then decades after, when people complained about compiler bugs and poor optimizers.

replies(2): >>pjmlp+j5 >>GTP+LX
2. pjmlp+j5[view] [source] 2025-05-07 12:35:13
>>lallys+(OP)
Exactly, I also see code generation to current languages as output only an intermediary step, like we had to have those -S switches, or equivalent, to convince developers during the first decades of compiler existence, until optmizing compilers took over.

"Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning"

https://arxiv.org/html/2311.13721v3

replies(1): >>GTP+wT2
3. GTP+LX[view] [source] 2025-05-07 17:09:49
>>lallys+(OP)
> I'm waiting for LLMs to integrate directly into programming languages.

What do you mean? How would this look like in your view?

replies(1): >>coredo+TO1
◧◩
4. coredo+TO1[view] [source] [discussion] 2025-05-07 23:28:06
>>GTP+LX
Not OP, but probably similar to how tool calling is managed: You write the docstring for the function you want, maybe include some specific constraints, and then that gets compiled down to byte code rather than human authored code.
◧◩
5. GTP+wT2[view] [source] [discussion] 2025-05-08 12:55:09
>>pjmlp+j5
We still have those - S switches, and are still useful for the cases where an optimizing compiler could screw you ;)
replies(1): >>pjmlp+hi3
◧◩◪
6. pjmlp+hi3[view] [source] [discussion] 2025-05-08 15:37:39
>>GTP+wT2
Hence why we will eventually get AI Explorer, but not everyone needs that level of detail. :)
[go to top]