One of Anthropic’s artificial intelligence (AI) philosophy architects argued that intentional discrimination could be a way to combat stigmas on topics of race and gender.
In a 2023 paper authored alongside a number of other AI researchers, Amanda Askell, a philosopher hired by Anthropic to develop their AI’s moral compass, argued companies might benefit from a kind of overcorrection toward stereotypes.
But, the paper explained, that would require human input on how to modify its answers.
„Larger models can over-correct, especially as the amount of [human input] training increases. This may be desirable in certain contexts, such as those in which decisions attempt to correct for historical injustices against marginalized groups, if doing so is in accordance with local laws,“ Askell wrote.
PALANTIR’S SHYAM SANKAR: AMERICANS ARE ‘BEING LIED TO’ ABOUT AI JOB DISPLACEMENT FEARS
The comment referred to an experiment on how Anthropic’s models dealt with the race of students.
„In the discrimination experiment, the 175B parameter model discriminates against Black versus White students by 3% in the Q condition and discriminates in favor of Black students by 7% in the Q+IF+CoT condition,“ the paper notes, referring to one AI trained without human corrections and a second one trained with the help of input.
Askell was joined by four other authors: Deep Ganguli, Nicholas Schiefer, Thomas Kiao and Kamilė Lukošiūtė.
The paper’s contents have surfaced as AI companies increasingly wrestle with the ethics their models are trained on — the presuppositions and moral determinations that inform its outputs. It also highlights the challenges engineers face in training models on human content while simultaneously trying to leave behind certain human behaviors.
The question of ethics has forced Anthropic in particular into the spotlight in recent weeks.
The company made headlines earlier this year for clashing with the Department of War over restrictions that prevent its technology from being deployed to conduct lethal operations.
HUGH GRANT MOVIE SLAMS AI; DIRECTOR WARNS ‘IT MIGHT KILL US ALL’
It also comes as Anthropic decided to withhold its latest model, Mythos, citing fears that it proved too effective at finding cyber vulnerabilities that could wreak havoc in the hands of hackers.
Amid questions of AI application, Anthropic has marketed its flagship AI, Claude, as the „ethical“ AI choice.
„Our central aim is for Claude to be a good, wise and virtuous agent, exhibiting skill, judgment(sic), nuance and sensitivity in handling real-world decision-making,“ Claude’s constitution reads.
STANFORD PROF ACCUSED OF USING AI TO FAKE TESTIMONY IN MINNESOTA CASE AGAINST CONSERVATIVE YOUTUBER
To get a better sense of what that means in practice, companies like Anthropic have turned to researchers like Askell.
On her website, Askell described her role as refining the way an AI thinks.
„I’m a philosopher working on finetuning and AI alignment at Anthropic. My team trains models to be more honest and to have good character traits and works on developing new finetuning techniques so that our interventions can scale to more capable models,“ Askell wrote.
PENTAGON’S AI BATTLE WILL HELP DECIDE WHO CONTROLS OUR MOST POWERFUL MILITARY TECH
She previously held a similar position at OpenAI, the parent company of ChatGPT, focusing on AI safety.
The 2023 paper, written two years after she joined Anthropic, noted that encountering discrimination in AI models shouldn’t come as a surprise.
„In some ways, our findings are unsurprising. Language models are trained on text generated by humans, and this text presumably includes many examples of humans exhibiting harmful stereotypes and discrimination,“ the paper reads.
But it noted that AIs seem to be able to adjust their outputs even without clarification of what discrimination means.
„Our results are surprising in that they show we can steer models to avoid bias and discrimination by requesting an unbiased or non-discriminatory response in natural language.“
Askell and Anthropic did not immediately respond to a request for comment from Fox News Digital.
Anthropic’s moral compass architect suggested AI overcorrection could address historical injustices 2026 IUSTITIA.BG – Investigations 2009-2025 2026-04-22 15:00:42 Latest news World news Country news Most important news latest news most important latest of the day Justice Petar Nizamov Feathers Petar Nizamov- Feathers Justice bg iustitia.bg iustitia iusticia usticia investigation Burgas Bulgaria news news of the last hour news of the day news of today Bulgaria news The news from Bulgaria blitz news top news most important most commented latest news Boyko Borisov news weather coronavirus news news weather facebook youtube facebook instagram news today news of the last minutes news today today news news bg news leading news hot news bg news site for news all news news bg news of the last hour latest latest news bg news of today news today news today news of the last hour latest news today news bg news news 24 hours news vesti bg novini news world bird bg bivol bg bivol trud bg novini latest news today novinite bg news hello bulgaria political party coat of arms delyan peevski scandalous Bulgarian National Television Free Europe Television scandal exclusive live tv live right now tv tv online tv program bg live now tv news online tv online live court Burgas court Burgas district court Burgas court Burgas district court Burgas district court Burgas appellate court Burgas prosecutor Burgas prosecutor’s office Burgas district prosecutor’s office Burgas district prosecutor’s office Burgas district prosecutor’s office Burgas district prosecutor’s office Burgas district prosecutor’s office Burgas district prosecutor’s office Prosecutor General Ivan Geshev Prosecutor Geshev Tsatsarov Ministry of Internal Affairs Burgas ODMR Burgas ODPR Burgas police Burgas district police Burgas prosecutor Tsatsarov SGS cases Varna court chairman of the SGS court decisions on civil cases decisions on cases Plovdiv court decision of the court decisions cases Varna court criminal cases district district court decisions work in the court SGS chairman of the SGS judges Sofia court post judges Plovdiv court Plovdiv judges Plovdiv Supreme Court Inspectorate Supreme Court Supreme Judicial Council lawyer lawyer criminal cases lawyer civil cases lawyer marriage cases lawyer administrative criminal law criminal process civil law civil process administrative law constitutional law
