Hacker News new | ask | show | jobs
by danielmarkbruce 315 days ago
An LLM is not a tool to allow you to add a layer of abstraction. It's a worker.
1 comments
didericis 315 days ago
It works by translating language abstractions to code.

The probability of plain english being correctly translated to code depends on existing code and documented abstractions describing lower level functionality.

link
danielmarkbruce 309 days ago
Not in any consistent or deterministic way, which is why it can't be used as a layer of abstraction.

Humans, for example, aren't a layer of abstraction. Having a team of engineers doesn't enable you to say "build X" and just forget about it.

link