zlacker

[parent] [thread] 14 comments
1. mrkurt+(OP)[view] [source] 2025-06-02 21:19:39
PLEASE write your response. We'll publish it on the Fly.io blog. Unedited. If you want.
replies(2): >>kubb+m1 >>ofjcih+C1
2. kubb+m1[view] [source] 2025-06-02 21:26:59
>>mrkurt+(OP)
Maybe make a video of how you're vibecoding a valuable project in an existing codebase, and how agents are saving you time by running your tools in a loop.
replies(2): >>metalt+16 >>andrep+x9
3. ofjcih+C1[view] [source] 2025-06-02 21:28:28
>>mrkurt+(OP)
I’m uninterested in giving you content. In particular because of your past behavior.

Thanks for the offer though.

replies(2): >>tptace+A2 >>throwa+L6
◧◩
4. tptace+A2[view] [source] [discussion] 2025-06-02 21:33:38
>>ofjcih+C1
Kurt, how dare you.
replies(1): >>ofjcih+ib
◧◩
5. metalt+16[view] [source] [discussion] 2025-06-02 21:52:19
>>kubb+m1
Seriously… thats the one thing I never see being posted? Is it because Agent mode will take 30-40 minutes to just bookstrap a project and create some file?
replies(2): >>csalle+b9 >>sensan+mv
◧◩
6. throwa+L6[view] [source] [discussion] 2025-06-02 21:57:08
>>ofjcih+C1
> past behavior

Do go on.

◧◩◪
7. csalle+b9[view] [source] [discussion] 2025-06-02 22:12:29
>>metalt+16
It takes like 2-6 minutes to do that, depending on the scope of the project
◧◩
8. andrep+x9[view] [source] [discussion] 2025-06-02 22:14:48
>>kubb+m1
So they can cherry pick the 1 out of 10 times that it actually performs in an impressive manner? That's the essence of most AI demos/"benchmarks" I've seen.

Testing for myself has always yielded unimpressive results. Maybe I'm just unlucky?

replies(1): >>kubb+0Z
◧◩◪
9. ofjcih+ib[view] [source] [discussion] 2025-06-02 22:25:32
>>tptace+A2
You wouldn’t happen to work for fly.io as well, would you?

Edit: Nm, thought I remembered your UN and see on your profile that you do.

replies(1): >>grzm+mb
◧◩◪◨
10. grzm+mb[view] [source] [discussion] 2025-06-02 22:25:54
>>ofjcih+ib
Yes. And the author of the submission.
replies(1): >>Mofpof+do
◧◩◪◨⬒
11. Mofpof+do[view] [source] [discussion] 2025-06-02 23:50:31
>>grzm+mb
OMG I didn't notice. Way to burn down a huge amount of respect stemming from past cryptography work in just one blog post.
replies(1): >>dogeco+TI
◧◩◪
12. sensan+mv[view] [source] [discussion] 2025-06-03 00:53:49
>>metalt+16
Well no, the reality of this workflow is the farcica, abject failures unleashed on the Dotnet codebase a week ago.

>>44050152

◧◩◪◨⬒⬓
13. dogeco+TI[view] [source] [discussion] 2025-06-03 03:17:46
>>Mofpof+do
it's irksome to see tptacek having his patio11 moment for sure.
replies(1): >>tptace+uM
◧◩◪◨⬒⬓⬔
14. tptace+uM[view] [source] [discussion] 2025-06-03 04:03:46
>>dogeco+TI
What does this even mean? (I should be so lucky.)
◧◩◪
15. kubb+0Z[view] [source] [discussion] 2025-06-03 06:18:01
>>andrep+x9
Livestream would be fair.
[go to top]