zlacker

[return to "Scaling long-running autonomous coding"]
1. tired_+Hg[view] [source] 2026-01-14 23:31:10
>>samwil+(OP)
The moment all code is interacted with through agents I cease to care about code quality. The only thing that matters is the quality of the product, cost of maintenance etc. exactly the thing we measure software development orgs against. It could be handy to have these projects deployed to demonstrate their utility and efficacy? Looking at PRs of agents feels a wrong headed, like who cares if agents code is hard to read if agents are managing the code base?
◧◩
2. icedch+Ak[view] [source] 2026-01-14 23:55:02
>>tired_+Hg
This is how we wound up with non-technical "engineering managers." Looks good to me.
◧◩◪
3. tired_+rs[view] [source] 2026-01-15 00:42:45
>>icedch+Ak
I think this misses the point, see the other comments. Fully scaled agentic coding replaces managers too :) cause for celebration all around
◧◩◪◨
4. icedch+lL[view] [source] 2026-01-15 02:55:56
>>tired_+rs
I don't believe that. If you go fully agentic and you don't understand the output, you become the manager. You're in no better position than the pointy-haired boss from Dilbert.
◧◩◪◨⬒
5. tired_+La3[view] [source] 2026-01-15 18:18:00
>>icedch+lL
Hey just wanted to thank you for the healthy back and forth! I respect your opinion and don't hold mine strongly. That said I'm eager for this space to mature and for us all to figure out the best way to interact with fault prone code generation tooling... Especially at scale where we all have the hardest time navigating complexity.
[go to top]