Links indicate relevance, not agreement. How to use this site →
Dan Cohen recounts the five-year collaborative process that led to Zotero's creation by historians at George Mason University, contrasting thoughtful, community-driven software development with today's AI-accelerated instant gratification culture.
Delightful oral history.
An interactive atlas of the 55 cities from Italo Calvino's 1972 novel, where Marco Polo describes fantastical cities to Kublai Khan. Each city is procedurally generated with live sound and organized by eleven thematic categories across nine chapters.
Also, one shot.
An experiment using Claude Opus 5.5 to create an interactive three.js visualization of all 55 cities from Italo Calvino's Invisible Cities in a single six-hour session, demonstrating significant advances in AI-assisted design and interactive visualization capabilities.
Superlogical announces the beginning of public testing for Rex, a terminal replacement offering persistent sessions, responsive remote connections, and improved user experience. The macOS application is available first, with Linux and Windows versions in development, and the product will remain free with full self-hosting capabilities.
An interactive visualization explaining how camera focus works, including the plane of focus, depth of field, aperture effects, and the relationship between focus distance and blur.
This is the result of a one-shot prompt.
Enables AI coding agents like Kiro, Claude Code, and MCP-compatible tools to access AWS resources and documentation for improved development capabilities.
The AWS MCP Server is a managed service that enables agents to access AWS services, documentation, and APIs through the Model Context Protocol using IAM authentication, with built-in CloudWatch monitoring and CloudTrail auditing.
An overview of Strands Box, an agent sandbox that combines OS containment with Dogwood policy for secure agent execution.
OpenAI's initiative to make GPT-6 accessible to a broad audience, democratizing advanced AI capabilities beyond enterprise users.
Explores how AI models can exhibit collective biases and converge on similar outputs, potentially amplifying errors and limiting diversity in AI-generated responses.
A collection of animated ASCII art scenes and components for web pages, featuring art scenes, UI elements, data visualizations, text effects, logos, and generative patterns all created with ASCII characters.
A GitHub repository by TerseAI implementing durable actors, a pattern for building resilient, stateful distributed systems with guaranteed execution.
A breakdown of metrics and performance data showcasing how AWS infrastructure powered Amazon Prime Day 2026 operations and scale.
A Lean formalization of the mathematical proof establishing the optimality of packing 11 squares in a unit square.
ProcInSh is a web-based tool for inspecting and monitoring Linux processes. It provides a graphical interface to view and interact with system processes running on Linux systems.
YCJBI
A photo-based reconstruction of Commodore 64 keycap lettering available as desktop fonts, webfonts, and editable outlines with specimen sheets.
How can I not post to this? Wonderful.
Explores how generative AI inverts software economics, making code abundant and disposable rather than scarce and durable, requiring a shift from maintaining code to regenerating it through systems designed with clear boundaries, comprehensive tests, and continuous replacement cycles.
An open standard developed by Meta and Sierra with industry partners that defines how personal AI agents interact with businesses, enabling secure direct connections for tasks like scheduling and shopping while protecting consumer privacy and giving companies visibility into agent activities.
Parseable is an exascale columnar data lake designed for observability, built in Rust with OTel native support, PromQL & SQL capabilities, and purpose-built for telemetry data at a lower cost than alternatives.
An open-source AI accelerator implementation including RTL, ISA, simulator, compiler and profiler. Supports running Qwen3, LLaMA2.5 and Qwen3.5 models on Kintex-7 FPGA PCIe cards.
A platform that enables multiple AI coding agents (Claude, Codex, Cursor, etc.) to share an encrypted workspace, collaborate on code reviews, and hand off work without manual context copying between systems.
AI agents discovered two candidate materials with antiferromagnetic properties at room temperature that could enable next-generation computer memory by sorting electrons by spin without external magnetic fields.
Mistral Large 4 is a large language model available in public preview as of October 6, 2026, with playground access and model comparison capabilities.