2026-11-18 08:12 UTC
In earnest, citing 1 year old researsh seems reasonable.
It’s more important to focus on more fundamental problems with LLMs, ie environnement cost, loss of skill, plagarizing of online content and agressive scrapin, … Less so on LLM and agents unreliability as technical fixes might improve reliability to a point where it’s no longer a problem. Frontier LLMs models are reportedly reliable enough for various coding tasks given supervision.
Replies (2)
-
@self@awful.systems 2026-11-18 08:17
in earnest, fuck off
-
@theodoraward@awful.systems 2026-11-19 14:49
reported reliability is goated