Skip to content
Sonic
AI
Sonic
AI
Home
Discover
Ask Sonic
Projects
Use with Claude or ChatGPT
Show me around
Request source or feature
The Future is Agentic in Recommender Systems, Sonic AI
Home
/
Data Skeptic
/
The Future is Agentic in Recommender Systems
Data Skeptic
Notify me
•
Apr 25, 2026
•
49:25
Interview
The Future is Agentic in Recommender Systems
From
Data Skeptic
Yashar Delju
(Associate Professor, Polytechnic University of Bari & Senior Research Scientist, guest)
Get the full transcript next time Data Skeptic releases an episode
Summary, key quotes, top claims, and the searchable transcript — emailed automatically. No card needed.
Sign up
Executive Summary
Large Language Models (LLMs) are fundamentally transforming recommender systems, shifting their core function from simple item ranking to fulfilling complex, multi-constraint tasks via conversational interfaces.
The adoption of LLMs introduces new and exaggerated risks, including highly persuasive hallucinations, context drift, and the amplification of societal biases, making trustworthy AI a critical concern.
Future recommender systems will likely be hybrid models, augmenting the reliability of mature techniques like collaborative filtering with the broad world knowledge and creative capabilities of LLMs.
The rise of AI agents requires new, multi-dimensional evaluation frameworks that go beyond traditional ranking accuracy to assess factors like hallucination, latency, and safety.
Continue your research
Keep pulling the thread on Yashar Delju.
The Evolution of Recommender Systems
Trustworthy AI in Recommendations
Emerging Risks of Generative Models
Or ask anything across 400+ expert conversations
12
quotes
Transcript
Key Arguments
Analysis
Quotes & Entities
12
Related
Loading transcript...
Processed May 4, 2026
Daily intelligence brief →
yt-dlp + mlx-whisper + Gemini