2026-04-29 06:20 UTC
Replies (5)
-
@danluu@mastodon.social 2026-04-29 06:26
I think a lot of the claims about LLMs increasing productivity by some huge factor (10x, 100x, 1000x) are overblown, but on testing/quality, the speedup is pretty incredible. It took me about an hour to do what would've previously taken me a week or two given that I'm not familiar with the project. It's not just startup cost, additional time is absurdly productive (maybe even more so) because a lot of time consuming manual work is automatable, which puts you in the right side of Amdahl's law.
-
@whitequark@social.treehouse.systems 2026-04-29 06:24
@danluu maybe the problem is that people don't want to make high quality software. maybe it's that LLMs enable people to not give a shit and they take it in droves which, I can excuse this for someone who is stuck in a position they can't meaningfully leave or they or their family suffers. but the most vocal proponents of not giving a shit that I've seen are people who are not in that position—some of them are people who could likely not work another day in their life and still be well-off
-
@shajra@functional.cafe 2026-04-29 06:26
@danluu Have you used Hegel yet? I think "fuzzing" is a little bit different in spirit than property-based testing, but the tools can seem similar. And the arguments about LLMs are the same for both fuzzing and PBT. Hegel's shrinking and caching story has worked out really well for me in practice. And I'm in a pretty normal language of just TypeScript. PBT has grown well past Haskell.
-
@almad@fosstodon.org 2026-04-29 06:56
@danluu I think we may rebound re: quality, but right now we’re just accelerating that software path dependence. LLMs were (in most orgs imho) introduced top down and need ROI, EMs are measuring easy thing which is tokens and features. Quality is still as hard to quantify as ever and bugs are still culturally hard for orgs to manage, so…it will just take some time.
-
@aristot73@infosec.exchange 2026-04-29 07:07
@danluu "Maybe I should write an updated version of that post for the LLM era?" Please do!