Do AI Models Learn Better Without Us?

Do AI Models Learn Better Without Us?
👋 Hi, I am Mark. I am a strategic futurist and innovation keynote speaker. I advise governments and enterprises on emerging technologies such as AI or the metaverse. My subscribers receive a free weekly newsletter on cutting-edge technology.

Do AI Models Learn Better Without Us?

Sometimes, the best way to help an AI learn is to stop helping. Turns out, too much supervision can stifle innovation. Yes, even for machines.

A study from Hong Kong University and UC Berkeley found that AI models generalize more effectively when left to learn on their own, challenging the long-held belief that hand-crafted training examples are essential.

Supervised Fine-Tuning (SFT), the current gold standard, often leads to memorization rather than true understanding, limiting a model’s ability to adapt to unfamiliar data. In contrast, reinforcement learning (RL) encourages models to create solutions independently, resulting in better performance on unseen examples.

However, combining both methods appears crucial. SFT stabilizes the process, while RL enhances the ability to generalize:

  • Reinforcement learning outperforms SFT for novel tasks.
  • SFT provides structure, ensuring output consistency.
  • RL-heavy models show untapped potential, especially for complex reasoning.

In a world driven by evolving data, adaptability is key. How will your organization strike the balance between structure and self-directed learning in its AI strategy?

Read the full article on VentureBeat.

----

💡 We're entering a world where intelligence is synthetic, reality is augmented, and the rules are being rewritten in front of our eyes.

Staying up-to-date in a fast-changing world is vital. That is why I have launched Futurwise; a personalized AI platform that transforms information chaos into strategic clarity. With one click, users can bookmark and summarize any article, report, or video in seconds, tailored to their tone, interests, and language. Visit Futurwise.com to get started for free!

Futurwise — personalized AI insights platform
Dr. Mark van Rijmenam

Dr. Mark van Rijmenam

Dr. Mark van Rijmenam is The Digital Speaker, a world-leading futurist and global AI keynote speaker who helps leaders decide what AI, and the technologies that follow it, mean for their business. He speaks to leadership teams at their retreats and to conference audiences worldwide, and his WAVE framework gives them a way of deciding that they keep using long after he has left the room. His Intelligence Age Scorecard measures how ready an organization is across the four WAVE pillars.

He holds a PhD from the University of Technology Sydney, is a Certified Speaking Professional and Global Speaking Fellow, and ranks among the world’s top futurists on the Global Gurus list (#1 in 2025, #3 in 2026). Salesforce named him one of its 16 leading AI voices. He has written six books, most recently Now What? How to Ride the Tsunami of Change, writes the Synthetic Minds newsletter on Substack, and founded Futurwise. Talk to his digital twin on WhatsApp: +1 (830) 463-6967.

Share