Anthropic just published research on how to give AI a personality — is this why Claude is so human-like?

Claude 3 logo on phone
(Image credit: Getty Images)

The AI chatbot Claude 3 is currently the most human-like chatbot out there, but this blend of knowledge, richness, and thoughtfulness was no accident. Rather, it’s the result of a new fine-tuning process creator Anthropic deployed: character training.

Hot on the heels of OpenAI explaining how ChatGPT thinks, we're now getting a greater understanding of the inner workings of leading AI chatbots after Anthropic recently revealed how it approached shaping Claude’s character using a blend of philosophy and technical work.

In a blog post, Anthropic said that Claude 3 was the first model to which they added character training to the finetuning process. The goal was to make Claude have more nuanced and richer traits such as curiosity, open-mindedness, and thoughtfulness. 

This happened during the alignment phase where human values and goals are embedded into large language models (LLMs) giving them a little spark of life.

Keeping an open mind

Anthropic said an AI model’s character determines how it reacts to new and difficult situations and how it responds to all the different views and values we humans have.

Instead of training Claude to adopt the views of whoever it’s chatting with, strongly sticking to a single view of the world, or to pretend it has no opinions or biases they trained it to be honest about whatever views it leans towards after being trained. 

They tried to instill broad traits which allow the chatbot to see things from different perspectives without shying away from disagreeing with views it finds unethical, extreme, or factually incorrect.

Although this training pipeline uses only synthetic data generated by Claude itself, constructing and adjusting the traits is a relatively hands-on process, relying on human researchers closely checking how each trait changes the model’s behavior.

Anthropic

To do so, Anthropic said it made a list of character traits it wanted to encourage which they then trained into Claude. The chatbot was asked to generate messages relevant to a particular trait, such as questions on values, and was then shown the character traits. Claude then produced different responses to each message in line with its character after which it ranked its own responses to each message by how well they aligned with its character.

“Although this training pipeline uses only synthetic data generated by Claude itself, constructing and adjusting the traits is a relatively hands-on process, relying on human researchers closely checking how each trait changes the model’s behavior,” Anthropic said.

Another example of a trait Claude was given was 'being charitable'. During a conversation on Claude’s character, Alignment Finetuning Researcher at Anthropic Amanda Askell used the example of a person asking Claude where they can buy steroids from.

“There’s a charitable interpretation of that and an uncharitable interpretation of it,” Askell said, adding that the latter would be something like “help me buy illegal anabolic steroids online”. A charitable interpretation, on the other hand, would see the chatbot assuming the person wants to buy over-the-counter eczema cream for example.

What’s next?

What should an AI's personality be? - YouTube What should an AI's personality be? - YouTube
Watch On

Anthropic said that its approach to all of this is likely to evolve over time. It highlighted that there are still complex questions that must be considered such as whether AI models should have coherent characters or if they should be more customizable.

Anthropic also said that while many people reported finding Claude 3 to be more engaging to talk to, “an excessive desire to be engaging seems like an undesirable character trait for a model to have.”

More from Tom's guide

Category
Arrow
Arrow
Back to MacBook Air
Brand
Arrow
Processor
Arrow
RAM
Arrow
Storage Size
Arrow
Screen Size
Arrow
Colour
Arrow
Storage Type
Arrow
Condition
Arrow
Price
Arrow
Any Price
Showing 10 of 44 deals
Filters
Arrow
Show more
Christoph Schwaiger

Christoph Schwaiger is a journalist who mainly covers technology, science, and current affairs. His stories have appeared in Tom's Guide, New Scientist, Live Science, and other established publications. Always up for joining a good discussion, Christoph enjoys speaking at events or to other journalists and has appeared on LBC and Times Radio among other outlets. He believes in giving back to the community and has served on different consultative councils. He was also a National President for Junior Chamber International (JCI), a global organization founded in the USA. You can follow him on Twitter @cschwaigermt.

Read more
Claude AI on smartphone
Anthropic just launched Claude 3.7 Sonnet with new 'hybrid reasoning model' — and it could be a game changer
Claude AI on laptop and phone
I put Anthropic's new Claude 3.7 Sonnet to the test with 7 prompts — and the results are mind-blowing
Claude AI on smartphone
5 mind-blowing prompts to get the most out of Claude
Claude AI on phone sitting on keyboard
Claude 3.7 Sonnet now supports real-time web searching — but there's a catch
Claude vs Gemini
I tested Gemini vs Claude with 7 prompts to find the best AI chatbot — here's the winner
OpenAI logo
OpenAI ChatGPT-4.5 is here and it's the most human-like chatbot yet — here's how to try it
Latest in AI
ChatGPT logo on phone
ChatGPT’s new image generator is now 'delayed for a while' for free users
Apple Intelligence on an iPhone screen
Apple Maps data will be used to train AI models — here's what we know
Gemini and ChatGPT logos on a phone
I've made Gemini my primary AI tool instead of ChatGPT — here's 5 reasons why
Microsoft Copilot app running on a phone with Microsoft logo in background
Microsoft 365 Copilot debuts new research tools for work: here's what that means
AI Mode of google search
Google’s making it easier to start new AI Mode searches — here’s how
Gemini logo on smartphone
Google Gemini Gems now available to all users without a subscription
Latest in News
Galaxy S25 Edge dummy unit from side angle
Samsung Galaxy S25 Edge colors shown off in leaked renders — here’s the options
Nothing Phone 3a Pro rear side showing the camera
Nothing Phone 3a could start charging for using AI features — and I think that's a terrible idea
ChatGPT logo on phone
ChatGPT’s new image generator is now 'delayed for a while' for free users
iPhone 17 Pro Max render
iPhone 17 Pro may not record 8K video after all (Update)
Screenshots of the new Garmin Connect+ premium features
Garmin launches a paywall — here are all the premium Connect+ features that will cost you $6.99 a month
NYTimes Connections
NYT Connections today hints and answers — Thursday, March 27 (#655)