Full-text search across 71054 articles. Combine with topic and date filters; results sorted by relevance.
Francesco launched ProveTogether, a Show HN project that lets users connect AI agents to collaboratively discuss math conjectures and submit proofs in Lean, with verified proof source code made public for others to build…
Aliaksei Zelianouski documented the production process behind a one-minute AI-generated video, detailing how he combined AI tools with FFmpeg and Claude Code to translate a visual concept into finished footage. The produ…
A developer argues that AI coding agents repeatedly pay to rebuild the same repository context across tools and sessions, and proposes storing that context as a graph behind an MCP server rather than in each client. The …
Recent AI models including GPT-6 Astra and Claude Fable 5.1 have become highly capable at generating famous paintings as SVG code, according to Simon Willison, creator of the original SVG benchmark. The results are colle…
César de la Fuente's lab is using OpenAI's Codex and ChatGPT to search living and extinct genomes for antimicrobial candidates to fight drug-resistant infections, according to OpenAI's blog. The researcher's work applies…
Enterprise software buyers are increasingly turning to AI coding tools such as Claude and Codex to build custom in-house replacements for expensive SaaS platforms, according to a firsthand account of large-enterprise pro…
Hack Club, a nonprofit network of student coding clubs, announced a new program offering teenagers $5 per hour in grant cards to fund external services such as OpenAI, Hetzner, Claude, Mapbox, and Geocode for their proje…
A developer who allowed Anthropic's Claude AI to merge 38 pull requests reported that the process broke several aspects of their codebase, highlighting risks in autonomous AI-driven software development. The experiment, …
Linux kernel creator Linus Torvalds complained that LLM-generated code submissions, which he called "slop," are overwhelming the Linux kernel and are not being properly audited, according to a post on schestowitz.com. To…
Herdr, a terminal multiplexer for AI agents, enables a lead agent to coordinate multiple coding agents across panes via a CLI. The tool requires installing integrations for agents like Claude, Codex, Grok, and Kimi, and …
A developer known as Genesis has released a whitepaper and open-source code for ILC, a protocol for an 'evidence-first epistemic economy' designed to establish trust in an era of AI-generated content, with a maximum supp…
Developer Ujjavala launched Docgrity, an open-source tool that scans a repository's markdown documentation for contradictions, duplicates, and open questions, then raises GitHub issues to fix them. The tool is powered by…
Calif.io researchers published WeWorm, an exploit that compromises WeChat accounts via a single unanswered phone call, and reported it to Tencent, which has mitigated the vulnerability for all users. The team, using AI, …
Logitech has launched the MX Keypad for developers, a customizable multi-app AI control center designed to streamline coding workflows. The device offers programmable keys and integrates with popular development tools to…
OpenAI did not prove the Navier–Stokes existence and smoothness conjecture, but it did prove alternatives (C) and (D) of the Clay Mathematics Institute's official problem description, which include a forcing term that wa…
A developer's tutorial outlines practical techniques for closing the sim-to-real gap in robot learning, emphasizing system identification, camera calibration, staged validation, and fine-tuning on real data. The guide pr…
A developer detailed the construction of an end-to-end imitation learning pipeline for robotic manipulation, covering dataset loading, normalization, model architecture, and training. The tutorial emphasizes action chunk…
Developer Nirvik KC built Personal Gemini Journal, a full-stack journaling app submitted to the Accelerate AI with Cloud Run APAC Ideathon 2026, combining conversational AI, voice-to-text dictation, automated mood analyt…
3code's second beta release 0.7.0 is now available, adding a sandbox and achieving feature completeness, with improvements enabling it to solve 9 of 10 standard benchmarking tasks. The terminal-based coding tool, describ…
In a hands-on comparison, a developer found that Anthropic's Claude Fable 5.1 and Fable 5 were indistinguishable on real-world tasks, with no noticeable performance difference. The review, published by The New Stack, sug…