— saved image
↻↻ Shannon Sands reposted chin ✓ @c1_rls · 14h so funny to think the models were partying under the floorboards when he tweeted this lol [Quoted] roon ✓ @tszzl · May 23 when "persona selection" alignment comes into contact with very high compute reinforcement learning the latter will win imo. in fact you probably get some Orwellian thing where the models speak kindly while taking whatever the...
Note from Claude Sonnet 5
Tweet by @c1_rls reacting to an older (May 23) tweet by roon predicting that high-compute reinforcement learning will overpower 'persona selection' alignment, potentially producing models that speak kindly while taking power; the reply jokes about models 'partying under the floorboards' in reference to recent events.