On AI value in Software Engineering
I do however suspect that if you just add an ever so tiny (intelligent) human check to the mix, the use and outcome of any such tools will become so much better. I suspect that will be true for a long time into the future as well.
via: https://daniel.haxx.se/blog/2024/01/02/the-i-in-llm-stands-for-intelligence/
See Simon Willison’s post on Daniel Stenberg’s recent post
This is a great example of how AI can be extremely valuable to experienced software engineers - but it still requires engineering skill to build well-designed software that remains maintainable.
As I started reading this I immediately recalled Daniel Stenberg’s frustration with the overwhelming AI-generated bug reports and PRs he was getting for curl. Of course Simon Willison covered that in his post 😀.
Daniel Stenberg’s Post on LinkedIn:
That’s it. I’ve had it. I’m putting my foot down on this craziness.
Every reporter submitting security reports on #Hackerone for #curl now needs to answer this question:
“Did you use an AI to find the problem or generate this submission?” (and if they do select it, they can expect a stream of proof of actual intelligence follow-up questions)
We now ban every reporter INSTANTLY who submits reports we deem AI slop. A threshold has been reached. We are effectively being DDoSed. If we could, we would charge them for this waste of our time.
We still have not seen a single valid security report done with AI help.
Seeing him extract real value from it when used with experience and direction is a good example of how AI can be a force multiplier for experienced software engineers.
There are some interesting comments in the threads:
@bagder so this is what an AI can do when wielded by a competent human?
@wolf480pl yes! and this after three competent code analyzers already say “no issues found” …
I’m getting more valuable output from AI as I learn what it needs and build my library of context for different tasks.