
Teaching AI agents to ask better questions by playing “Battleship”
MIT researchers use the classic game as a test bed for AI agents, finding a small AI model can outperform the biggest ones at 1 percent of the cost.
Open originalAgentic AI systems, coding agents, computer-use agents, tool use, orchestration, and agent safety signals.

MIT researchers use the classic game as a test bed for AI agents, finding a small AI model can outperform the biggest ones at 1 percent of the cost.
Open original
GPT-Rosalind advances life sciences research with enhanced biological reasoning, medicinal chemistry expertise, genomics analysis, and experimental workflow capabilities.
Open original
Sepehr Khosravi discusses the evolution of developer productivity tools. Evaluating the strengths of tools like Cursor and Claude Code, he explains actionable techniques for senior engineers - including context engineering, custom rules, and Model Context…
Open original
Adding MCP Tools to Reachy Mini
Open original
Holo3.1: Fast & Local Computer Use Agents
Open original
The global health care sector is under increasing strain.  Decades of chronic underinvestment and constraints in recruitment have coincided with a surge in demand for services for aging populations. Gaps in provision are already taking a toll, with…
Open original
Discover new Codex plugins, sites, and annotations that help analysts, marketers, designers, investors, and other teams get more done with AI.
Open original
The Next Era of Knowledge Work report explores how Codex is transforming productivity through AI-powered research, data analysis, workflow automation, and content creation.
Open original