zlacker

> Every line was thoroughly reviewed and cross-referenced with relevant RFCs, by security experts with previous experience with those RFCs.

This sounds like coding but slower

>>teaear+(OP)
The point was validating a hypothesis. That is the validation part.

>>teaear+(OP)
I would say it ended up being much faster than had I written it by hand. It took a few days to produce this library -- it would almost certainly have taken me weeks to write it myself.

>>kenton+R2
If you had written it by hand would the verification process been as time consuming?

i.e. overall including the time spent verifying that it was correct, do you consider it a net win?

>>noodle+D5
I was already including my own time spent verifying the output, which I mostly did right away as the code was being generated (approving or rejecting each edit).

And the separate security review would have been required either way.

So yes, it saved time.

>>kenton+R2
does reviewing have the same fidelity as writing ?

reminded me of my university classes where i took my own notes vs studied someone else's notes. you can guess which one was superior.

>>apwell+2i
It's certainly true that my own recall of the code would be better if I had written it by hand.

But I don't think the final code is all that far off from what I would have written.

>>kenton+R2
> It took a few days to produce this library -- it would almost certainly have taken me weeks to write it myself.

As mentioned in another comment >>44162965 I think this "few days" is unrealistic given the commit history. I think it would be more accurate to say it allowed you to do something in under one month that may have have taken two. A definite improvement, but not a reduction of weeks to days.

Or is that history inaccurate?

>>srhtft+zf1
I replied there: >>44165668

>>kenton+e9
Did you wrote it from scratch to compare? There's an old motto devs use all the time, you know. Measure first, don't guess. How do you know it would not have took you the same time or less to write the program if it was you? Or if for example, if you were using the AI to write the boilerplate for you while you focused on the core of coding? Or using it as a tab completor assistant instead of it being an agent? Saying it saved you time is easy when you don't have the data to back it up, it's easier than thinking that maybe, maybe this was not that good of an use of your time.

>>TeMPOr+t
You don't validate an hypothesis without testing counterfactuals, tho.