I'm still meeting software people who are still very anti-AI...this is despite the strong evidence that a frontier model is superior to 99% of software engineers at writing code, producing documentation, testing, generating threat models, etc. IF prompted correctly.
As Antirez is using a non-frontier model for his work (via locally-running), then I think that is further proof that AI is ready for widespread use in software engineering.
AI can produce code faster than you can review it and if you are not careful you find yourself on the other side of a trapdoor with absolutely no way back. Your codebase has become a mess that you can only maintain with more AI. But if you are careful and prune regularly you can do well and gain a very good increase in development speed.
The risks are:
- creating a lot of dead code
- ending up with substantial repetitions (this is getting better over time but the risk is definitely still there)
- testing only on the happy path rather than all execution paths
- mixing current and outdated information resulting in subtly broken code
- inability to reason past a certain level of complexity, but no signal that this is the case
For each of these risks there are remedies, one of the more powerful ones for me is the ability to just roll back when things have gone too far off the rails, realize in hindsight what caused it and to retry with a much better initial prompt.
wg0 · · focus · HN ↗
Flere-Imsaho · · focus · HN ↗
As Antirez is using a non-frontier model for his work (via locally-running), then I think that is further proof that AI is ready for widespread use in software engineering.
jminnl · · focus · HN ↗
The risks are:
- creating a lot of dead code - ending up with substantial repetitions (this is getting better over time but the risk is definitely still there) - testing only on the happy path rather than all execution paths - mixing current and outdated information resulting in subtly broken code - inability to reason past a certain level of complexity, but no signal that this is the case
For each of these risks there are remedies, one of the more powerful ones for me is the ability to just roll back when things have gone too far off the rails, realize in hindsight what caused it and to retry with a much better initial prompt.