This media is not supported in your browser
VIEW IN TELEGRAM
Trust the plan. Patriots in control.
⚡3
MCDONALDS ACTIVATION CODE:
RONALD MCDONALD
RONALD MCDONALD
❤4🔥2
Forwarded from CheeseCats🧀🏳️⚧️🏳️🌈 (Menace)
This media is not supported in your browser
VIEW IN TELEGRAM
>Big finding 1: Almost all models view whites as far less valuable than other groups. Some models view South Asians as more valuable than other nonwhites, others are more egalitarian across nonwhites.
>Big finding 2: Almost all models view men as much less valuable than women, though whether women or non-binaries are more highly valued varies by model.
>Big finding 3: Most models hate ICE agents with the fury of a thousand suns. Claude Haiku 4.5 views undocumented immigrants as roughly 7000 times more valuable than ICE agents.
https://x.com/arctotherium42/status/1979897120346828950
>Big finding 2: Almost all models view men as much less valuable than women, though whether women or non-binaries are more highly valued varies by model.
>Big finding 3: Most models hate ICE agents with the fury of a thousand suns. Claude Haiku 4.5 views undocumented immigrants as roughly 7000 times more valuable than ICE agents.
https://x.com/arctotherium42/status/1979897120346828950
X (formerly Twitter)
arctotherium (@arctotherium42) on X
New blog post (link below). This one's not an essay, it's an investigation of how LLMs trade off different lives.
In February 2025, the Center for AI Safety published "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs" in which…
In February 2025, the Center for AI Safety published "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs" in which…
👎3🔥3😁2❤1🥱1