Comment by zephen
16 hours ago
Don't worry! It'll only get better, as the amount of ouroboros training data explodes.
Weren't we taught that recycling is good?
16 hours ago
Don't worry! It'll only get better, as the amount of ouroboros training data explodes.
Weren't we taught that recycling is good?
Seems to be that just like scrum, AI eventually turns terrible code into passable code, and good code into passable code.
We're getting drowned by "good enough". Not "good" mind you, just "good enough".
> Seems to be that just like scrum
Any methodology or tool, really. Eventually, we're all just participating in cargo cults.
https://en.wikipedia.org/wiki/Regression_toward_the_mean
> Don't worry! It'll only get better, as the amount of ouroboros training data explodes.
Well, the AI can at least be constrained to "the code actually compiles, runs, and produces the correct output."
The number of internet answers that can't pass that bar is distressingly high.
> "the code actually compiles, runs, and produces the correct output."
I mean, I guess I interpreted the chart in tfa to indicate that this doesn't always happen.