From building an AI research tool to prompting the research itself

Technical Report: Playing Pretend: Expert Personas Don't Improve Factual Accuracy

[vc_row martech_row_background_position=”None” css=”.vc_custom_1742942106856{margin-bottom: 24px !important;}”][vc_column][/vc_column][/vc_row][vc_row martech_row_background_position=”None” css=”.vc_custom_1750970721780{margin-bottom: 40px !important;}”][vc_column width=”5/6″ css=”.vc_custom_1750970738029{margin-bottom: 40px !important;}”][vc_column_text css=”.vc_custom_1764963741477{margin-bottom: 1em !important;}”]This study investigates whether persona prompting improves AI performance on challenging academic benchmarks. We find that despite widespread adoption, assigning expert personas (e.g., “You are a world-class physics expert”) does not reliably improve accuracy. Domain-mismatched…Read More

wharton-generative-ai-labs/AIBO

An open-source tool for running controlled behavioral experiments on AI systems at scale.

Meet Foundry: An AI Startup that Builds, Evaluates, and Improves AI Agents

Tiles Notebook | Note Taking Tool With AI Agents

A notebook that makes working with AI agents easier.

Arvind Narayanan on Twitter / X

To understand and empathize with how workers in many or most fields outside software experience advances in AI capabilities, I propose a little thought experiment. https://t.co/QZG24aRiBe— Arvind Narayanan (@random_walker) July 28, 2026

CSS Studio. Design by hand. Code by agent.

A visual CSS editor in your browser. Adjust styles with sliders and pickers, and your AI agent writes the changes to source.

Science that Compounds: The Need for A New Substrate for Research in the Age of AI

This paper is a perspective from Lightcone Research, an open-source initiative building tooling for scientific research in the age of agentic AI.

I love AI, but it still can't design for shit

Without a critical human eye, AI produces slop. The quality bar is yours to maintain.

I used AI. It worked. I hated it.

I used Claude Code to build a tool I needed. It worked great, but I was miserable. I need to reckon with what it means.

Model Hardware Standard

A new standard for AI agents to safely operate physical equipment in scientific research and advanced manufacturing.

Import AI 461: "Alignment is not on track"; FrontierCode; and synthetic research interns

Where are your agents right now?

AI agents team up in Agent Laboratory to speed scientific research

Johns Hopkins University and AMD have developed Agent Laboratory, a new open-source framework that pairs human creativity with AI-powered workflows.

Lightcone Research

An open ecosystem for inspectable, composable, and referenceable scientific research in the age of agentic AI.