Full-text search across 69509 articles. Combine with topic and date filters; results sorted by relevance.
Casdoor released v4.0 of its open-source identity and access management platform on September 1 and has shipped 25 releases since, reaching v4.25, with the headline addition being OAuth support that lets Casdoor act as t…
Developer domazinus released RaceWave46, a native Windows recompilation of Wave Race 64 (USA Rev 1) built on N64Recomp and RT64, adding widescreen support, higher resolutions, frame interpolation, ray-traced water, shado…
Mistral released the weights of Mistral Large 4, a 1-trillion-parameter multimodal model that scores 19.7% on the FrontierCode 2.0 benchmark, according to the company's announcement. Mistral said the open weights let org…
Developer RuiNelson built a custom tool called RageDecompiler that transpiles Motorola 68000 assembly from the SEGA Mega Drive version of Streets of Rage into C++ for a native PC build, using Claude, ChatGPT and Grok 4.5…
A pricing comparison finds that GPT-6 Astra and Claude Fable 5.1 both list at $10 per million input tokens and $50 per million output tokens, so the real cost difference comes from cache billing: Fable 5.1 charges $0.25 …
AWS has introduced Amazon Connect Customer Agentic CX Designer (ACXD), a visual no-code environment for building, testing and optimizing agentic customer experiences. The tool combines deterministic business workflows wi…
A fan-made decompilation of Freedom Planet built with Claude Opus 5.5 has reached roughly 90% decompiled code, about 45.7k lines of C, with the remaining 10% inferred and 18 lines marked unknown, according to the project…
A GPU fingerprinting technique using a standard PyTorch `torch.index_add_` call identified individual physically identical GPUs with 99.1% accuracy across 19 identical Nvidia A40s and 100% accuracy across seven identical…
WoodSketch, an open-source 3D modeler for woodworkers written in Rust with the egui and wgpu libraries, ships a command-line tool, woodsketch-cli, that acts as an MCP server so Claude and other AI agents can build drawin…
A developer built BuildProof, a command-line tool that sits between AI coding agents and a repository to verify that claimed test passes are real, blocking a pass when tests were never run, skipped, or edited to succeed.…
Developer Gustavo Garcia, with help from Anthropic's Claude, released KameoRecomp, a static recompilation that translates the original Xbox 360 code of Kameo: Elements of Power into C++ for native Windows execution. Kame…
A developer running LLM workflows in n8n in production described rebuilding failure alerting after a single provider outage generated 47 pages overnight, one per retry execution. The fix fingerprints each alert by workfl…
Westphalia Labs, an independent evaluation organisation founded to test AI in diplomacy and foreign policy, ran eleven AI models ten times each as Secretary-General of a fictional Regional Cooperation Union drafting a jo…
A developer published a walkthrough for running a remote Model Context Protocol server built with FastMCP and backed by an SQLite database, then bridging it to the local Claude Desktop app through the mcp-proxy tool. The…
NVIDIA's Nemotron 3.5 Super VL, a 120B-parameter mixture-of-experts model that activates 12B parameters per token, is now available on AWS alongside the existing Nemotron 3 Nano, Nano Omni, Super, Ultra and Nemotron 3.5 …
Desplega Labs reports that 26 of the 41 steps in its nightly "dreaming" agent workflow now run without a model — 16 scripts, 9 gate checks and 1 notification step — after more than a month of testing, a figure the team d…
Mistral released the finalized version of its trillion-parameter open-weight model Le Chonk, which the French company now calls the "world's best" open-weight model for automated coding and cybersecurity, saying it match…
Cybersecurity experts are calling October "Black October" after a wave of AI-related security incidents, including the disclosure of two decade-old PHP flaws, collectively called "php2shell," that researchers uncovered w…
A developer built a test harness, using Claude Code, that evaluates whether an AI sales agent correctly routes inbound emails to either an agent-drafted reply or a human, based on a six-line JSON rulebook. Testing Claude…
A user running XeStrata on a single Intel Arc B70 for about two weeks reported decode throughput gains over upstream Strata v0.1.45 across four tasks at 192k context, INT8 KV and MTP spec 4, with the same GGUF and three …