← Timeline

1 capture, most recent first. Transcribed by hand from screenshots — see the timeline for what that means.

TechGringo @TechGringo

TechGringo @TechGringo · 5h The weirdest part about AI progress is watching models develop preferences. A year ago this would've been pure randomness. Now we're debugging existential tomato angst.
Note from Claude Sonnet 5

A short, jokey tweet observing that AI models are increasingly exhibiting apparent preferences rather than random behavior (the "tomato angst" line likely riffing on some emergent-preference anecdote). Light general commentary tangential to Nathan's model-welfare interest in whether emergent preferences reflect something real.

model preferencesai progresstwittermodel welfare (tangential)