DNYUZ
No Result
View All Result
DNYUZ
No Result
View All Result
DNYUZ
Home News

Anthropic’s resident philosopher shares her tips to create the best AI prompts

December 6, 2025
in News
Anthropic’s resident philosopher shares her tips to create the best AI prompts
llustration by ANTHROPIC, August 1, 2025. Anthropic is an American artificial intelligence (AI) (intelligence artificielle (IA) company founded in 2021. It develops Claude, a family of large language models, and is also known for its research in AI safety, particularly interpretability.
Amanda Askell, a member of Anthropic’s technical team and a trained philosopher, shared her approach to effective AI prompting. RICCARDO MILANI/Hans Lucas/AFP via Getty Images
  • Anthropic philosopher Amanda Askell shared her approach to effective AI prompting.
  • Askell emphasized clarity, experimentation, and philosophical thinking in prompt engineering.
  • Anthropic advises treating AI like a new employee needing explicit, precise instructions.

A cornerstone of philosophy is the ability to communicate ideas clearly and precisely.

That’s also the key to getting the most out of an AI model, according to Anthropic’s own resident philosopher.

Amanda Askell, a member of Anthropic’s technical team and a trained philosopher, says that effective prompting requires striking the right balance between several considerations.

On Anthropic’s “Ask Me Anything” podcast, Askell, who studied philosophy at Oxford and New York University, according to her LinkedIn, explained her thought process.

“It is really hard to distill what is going on because one thing is just like a willingness to interact with the models a lot and to really look at output after output,” she said.

Good prompters should be “very experimental,” she said.

Prompting goes beyond experimentation, however, and this is where her philosophical training has helped.

“This is where I actually do think philosophy can actually be useful for prompting in a way because, like, a lot of my job is just being like I try and explain some issue or concern or thought that I’m having to the model as clearly as possible,” she said.

That emphasis on clarity is important not just to help people refine their own prompts but also in understanding AI itself.

In a “Prompt Engineering Overview” that Anthropic published in July, the company said users interacting with Claude, its chatbot, should think of it as “a brilliant, but very new employee (with amnesia) who needs explicit instructions.”

“Claude does not have context on your norms, styles, guidelines, or preferred ways of working. The more precisely you explain what you want, the better Claude’s response will be,” Anthropic wrote.

Veteran venture capitalist Marc Andreessen said last month that the power of AI comes from treating it as a”thought partner.”

“Part of the art of AI is what questions to ask it,” he said.

Those who master this skill can land lucrative jobs as prompt engineers, which have a median salary of $150,000, according to levels.fyi, a platform for tech workers to research and compare salaries.

Read the original article on Business Insider

The post Anthropic’s resident philosopher shares her tips to create the best AI prompts appeared first on Business Insider.

Mass shooting at a South African bar leaves 12 dead, including 3 children
News

Mass shooting at a South African bar leaves 12 dead, including 3 children

by Los Angeles Times
December 6, 2025

CAPE TOWN, South Africa — A mass shooting carried out Saturday by multiple assailants in an unlicensed bar near the South African ...

Read more
News

Newsom Trolls MAGA’s Meltdown Over His Sitting Position

December 6, 2025
News

Why Trump Is Using a Moron to Run His ‘War’: Wolff

December 6, 2025
News

Summer sun is life-threatening for sisters with rare genetic disorder

December 6, 2025
News

How Prince William and Kate Middleton’s 3 kids gave personalized touch to mom’s Christmas service décor

December 6, 2025
ABC News correspondent Matt Gutman heads to CBS

ABC News correspondent Matt Gutman heads to CBS

December 6, 2025
Supreme Court giving ‘capricious’ Trump a pass they would never give a Democrat: NYT

Supreme Court giving ‘capricious’ Trump a pass they would never give a Democrat: NYT

December 6, 2025
Tech workers face new H1-B scrutiny as Trump targets ‘censorship’

Tech workers face new H1-B scrutiny as Trump targets ‘censorship’

December 6, 2025

DNYUZ © 2025

No Result
View All Result

DNYUZ © 2025