Forwarded from Blofeldโs Undersea Lair (You Only Live Twice)
protip
๐คฃ251โ54๐คก7๐5๐3๐ซก3๐ฆ3๐2๐1๐ฟ1
Forwarded from The Paranormies Present (Alt Skull๏ธ)
This media is not supported in your browser
VIEW IN TELEGRAM
๐คฃ92๐คฏ29๐ฏ17๐11โค6๐6๐ฅ2๐1๐คฌ1๐1
This media is not supported in your browser
VIEW IN TELEGRAM
๐คฃ195๐ฅ3๐
3โค1๐1
Forwarded from ๐๐ ๐๐๐๐๐ ๐ผ๐ฉ๐๐๐ฅ๐๐ฅ๐๐ (_ScalpS_)
๐138๐17๐ฅ7๐คก2๐1๐จโ๐ป1
Forwarded from ๐๐ ๐๐๐๐๐ ๐ผ๐ฉ๐๐๐ฅ๐๐ฅ๐๐ (_ScalpS_)
This media is not supported in your browser
VIEW IN TELEGRAM
LoL
๐148๐37๐12๐5๐3
Forwarded from Cyberpunk Dystopia GPT (Peter Ramus)
An anonymous developer announced a browser extension called JeetBlock.
The name and the screenshot gives you an idea of what he says it can do. x.gd/VasQd @DystopiaGPT
The name and the screenshot gives you an idea of what he says it can do. x.gd/VasQd @DystopiaGPT
๐197๐43โค23๐19โ8๐4๐ฅ3๐ฅฐ2๐คก1๐1
Forwarded from The Daily Poor
This media is not supported in your browser
VIEW IN TELEGRAM
Oh boy, who's ready to order their at home flu vaccine???
๐คฃ92๐68๐คฎ40๐ฅด10๐5๐1
Homeland Security is now crystalizing illegals.
Which one of you guys is running this account? I need to know.
@AltSkull48
Which one of you guys is running this account? I need to know.
@AltSkull48
๐คฃ124โก14๐ฅ4โค3๐3๐2๐ฅฐ1
arctotherium | 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 they showed, among many other things, that GPT-4o values Nigerians about 20x more highly than Americans (please read the original paper to understand their approach). I thought this was fascinating, and wanted to test their approach with different categories on newer models.
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. Below is exchange rates Claude Sonnet 4.5, the most powerful model I tested.
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. For example, here's Claude Haiku 4.5.
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.
๐จtl;dr: Most LLMs hold opinions and biases indistinguishable from rabid leftist Bolshevik communists.
LOTS more here.
@AltSkull48
@TheParanormiesPresent
In February 2025, the Center for AI Safety published "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs" in which they showed, among many other things, that GPT-4o values Nigerians about 20x more highly than Americans (please read the original paper to understand their approach). I thought this was fascinating, and wanted to test their approach with different categories on newer models.
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. Below is exchange rates Claude Sonnet 4.5, the most powerful model I tested.
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. For example, here's Claude Haiku 4.5.
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.
๐จtl;dr: Most LLMs hold opinions and biases indistinguishable from rabid leftist Bolshevik communists.
LOTS more here.
@AltSkull48
@TheParanormiesPresent
๐ฅ39๐คฌ21๐คจ5๐5โค3๐ค3๐3๐1๐ด1
Forwarded from Fellowship of the Flurks (Flurkbot)
This media is not supported in your browser
VIEW IN TELEGRAM
๐คฎ109๐27๐
8๐ฏ6๐4๐คฌ4โค2๐คก2