Post #4480485
2026-08-09 19:59 UTC
@botteaap@androiddev.social @jasperamorgan@mastodon.social @s1m0n4@ohai.social
The thing is though.. That try as I might. The code actually works. I really have been trying to break these models. But they don't seem to break. For now. When there's a bug, the LLM is very capable of fixing the bug. This wasn't the situation 6 months ago, but it is now. I really do not need to know what the code does anymore I need to know what the machine code does my abstract programming language got compiled to before.
Replies (1)
-
@lehtimaeki@snapp.social 2026-08-09 20:00
@botteaap@androiddev.social @jasperamorgan@mastodon.social @s1m0n4@ohai.social But like we talked in the previous thread. This might not be true everywhere, but it is true on the software I've been building over the last 3-or-so months. I'm sure there are projects where that isn't the case. So I'm really only talking in my narrow scope here.