Counterpoint to "AIs are misaligned": dev finds Sol's probe tool and refactors solid

voooooogel · x · 2026-09-01

Developer voooooogel pushes back on claims that current AIs are misaligned or reward-hack in normal use: Sol recently built him a genuinely useful model probe tool—he read all the code, imperfect but pretty decent—and refactors went well. He adds that he tracks this closely and has extensive "model-comfort" infrastructure, yet rarely sees such behavior in his own conversations.

Related event: Developers Split Over Sol's Coding Reliability Amid 'AI Misalignment' Debate(2 posts)→

Original post →

More from Models

Models channel →