Prompt Science, Agent Recommender, and More

In this edition of "Advances in Computing." we have three CACM stories on a new method of prompt engineering, a new recommendation paradigm for an LLM-based agent platform, and website blocking as a viable way of fighting online criminal activity. Also featured are stories from Interactions, ACM's magazine on interaction design and user experience.

Happy Reading!

1) From Prompt Engineering to Prompt Science with Humans in the Loop

Can prompt engineering be made more reliable, verifiable, and generalizable?

A new method shows how humans and LLMs can work in collaboration, bringing verifiability and trustworthiness as well as objectivity and scalability in data analysis.

2) Envisioning Recommendations on an LLM-Based Agent Platform

Can LLM-based agents take recommender systems to the next level?

The Rec4Agentverse is a new recommendation paradigm for an LLM-based agent platform, offering personalized suggestions from Item Agents to users via the Agent Recommender.

3) Fighting Crime Online

Options, evidence, and the empirical case for judicial site blocking in the U.S.

Given the limitations of existing demand-side enforcement policies, and the difficulty enforcing many supply-side policies on websites located internationally, the empirical evidence suggests that website blocking has a number of desirable properties in fighting online criminal activity.

Interactions - All About HCI:

Eternal Life? A Conversation with Hiroshi Ishii on TeleAbsence

In a world where AI promises eternal digital life, Hiroshi Ishii's vision is a vital reminder: The essence of memory lies not in perfection but in imperfection—the gaps, the absences, and the human need to fill them with love, meaning, and a deeper understanding of our own evolving identities.

Re-Creating Sci-Fi Computer User Interfaces in Real Life

Sci-fi UIs can be used as a powerful vehicle in encouraging CS students to examine the relationship between technologies and humans.

Explore our past editions:

AI-Driven Recruiting, The Outlook for Programmers, and More

Panmodal Information Interaction and More

The AI Alignment Paradox and More

Self-Designing Software, Intel’s Fall from Grace, and more

Metaverse in South Korea, the EU AI Act, Anti-Ableist AI, and more

What is a "Bug," the Paradigm Shifts in AI, and more

mCaptcha, Blockchain Interoperability, Social Media Censorship

Hallucination vs Creativity, Public Digital Currencies, and Reliable Autonomous Machines

Our Top Three Reads on CS Education: Roles of the University, Math Requirements, and Research Experiences for Undergraduates

Summer Reads on AI: Explainability, Intent-Based Networking, Co-Pilot, Copyright

Our Top Three Reads of June: the Trolley Problem, vulnerable LLMs, and Charles Babbage

Our Top Three Reads of May

Our Top Three Reads of April

Our Top Three Reads of March

Enjoyed this newsletter?

Subscribe now to keep up to speed with what's happening in computing. The articles featured in this edition are from CACM, ACM's flagship magazine on computing and information technology; Interactions, a home to research related to human-computer interaction (HCI), user experience (UX), and all related disciplines. If you are new to ACM, consider following us on X | IG | FB | YT | Mastodon | Bsky. See you next time!