Jason GormanIf I think of all the levers I could pull to improve the performance of a software development team, the data's clear that "AI" code generation has so little leverage where team outcomes are concerned that I doubt it would even be on the list.
Milan Todorov
- 4 Followers
- 21 Following
- 106 Posts
aProgrammingExtremist
@d_stepanovic
My parents were psychos who left me traumatized. So it is their fault that I terrorize ppl now. Hands off me please!
My parents were psychos who left me traumatized. So it is their fault that I terrorize ppl now. Hands off me please!
@simeon Yup. They got the car up to 200 mph on a straight road with no other cars around, and mistakenly think they could drive through rush hour traffic at the same speed.
Kevlin HenneyA lot of security is based on trust. Trust relies on competence. The security theatre I get from a lot of sites and apps, sometimes elaborated through MFA, does not inspire such trust.
That device you tell me is unrecognised? It's the one I've used to access the app every day for at least the last year.
If you want to convince me your app is secure, start with competence. Poorly engineered products don't do that. KPI-driven product staff don't do that.
Dragan Stepanović"We can't afford understanding the code we're deploying to production because that way we can't keep up with the pace at which LLMs generate code."
That's a tail wagging the dog instead of the opposite.
In an industry where burnout is The Norm, let's just use AI to do more and more of what we do.
I can't see how that can backfire in any way.
I can't see how that can backfire in any way.
@kevlin, so you turned a bug into a missing feature. Noice.
@jasongorman
"but the project is so complicated, it's not possible to write a test for such complicated code before the code itself".
"but the project is so complicated, it's not possible to write a test for such complicated code before the code itself".
craignicol@jasongorman but without a backlog how would we keep track of the low priority work that's never going to get done?
@JeffGrigg, the majority of the code out there in the open is really crap, so that's what the LLMs have seen, and that's what they are going to spew. Tons of it.