←back to thread

The rise of async AI programming

(www.braintrust.dev)
123 points mooreds | 1 comments | 11 Sep 25 12:20 UTC | HN request time: 0s | source
Show context
lelanthran ◴[11 Sep 25 15:14 UTC] No.45212622[source]▶
This works until you get to the point that your actual programming skills atrophy due to lack of use.

Face it, the only reason you can do a decent review is because of years of hard won lessons, not because you have years of reading code without writing any.

replies(7): >>45212731 #>>45212756 #>>45213395 #>>45213636 #>>45213875 #>>45213884 #>>45214429 #
sevensor ◴[11 Sep 25 16:48 UTC] No.45213636[source]▶
What the article describes is:

1. Learn how to describe what you want in an unambiguous dialect of natural language.

2. Submit it to a program that takes a long time to transform that input into a computer language.

3. Review the output for errors.

Sounds like we’ve reinvented compilers. Except they’re really bad and they take forever. Most people don’t have to review the assembly language / bytecode output of their compilers, because we expect them to actually work.

replies(1): >>45214191 #
ako ◴[11 Sep 25 17:45 UTC] No.45214191[source]▶
No, it sounds like the work of a product manager, you’re just working with agents rather than with developers.
replies(5): >>45214841 #>>45214888 #>>45215106 #>>45221459 #>>45224563 #
1. sevensor ◴[12 Sep 25 12:34 UTC] No.45221459{3}[source]▶
What I described is precisely the reception of early compilers. How is the LLM different? It’s slower? Its input looks more like natural language? Its output is less reliable? It runs on somebody else’s computer? What’s the essential difference between these two technologies that transform one text into another?