Full-text search across 71060 articles. Combine with topic and date filters; results sorted by relevance.
Lowkey Studio, an open source shader-powered visual effects compositor that runs in the browser, has been released as part of the Lowkey Media Viewer project. The tool allows users to layer shader chains and write custom…
A developer announced siza, a harness that pairs a local LLM with a Sabela notebook to improve Haskell code generation for data work, addressing issues like hallucinated modules and small context windows in models under …
Aidbase's MCP server implementation enables a self-healing support loop by allowing large language models to write to knowledge bases, not just read from them. The server includes tools like `add_aidbase_faq_item` and `a…
Microsoft has open-sourced its ML Video Codec (MLVC), a machine learning-based video compression technology designed to improve efficiency and quality. The release on GitHub includes the codec's source code, models, and …
Hugging Face released a new tool called 'Am I in the Stack?' that allows users to check if their code or data is included in The Stack, a large dataset used to train AI models. The tool, available as a Hugging Face Space…
Anthropic's Opus 5 model is nearly as capable as Fable 5, according to a comparison by the company. The new AI model shows significant improvements in reasoning and coding tasks, narrowing the gap with leading competitor…
Anthropic has released Claude Opus 5, its latest large language model, which demonstrates significant improvements in reasoning, coding, and multilingual capabilities over previous versions. The model sets new state-of-t…
A technical analysis argues that large language models (LLMs) structurally fail at long-horizon planning and physical reasoning due to autoregressive drift, while world models—such as those using latent space dynamics or…
A developer describes a common pitfall in PyTorch binary classification where high accuracy (92%) on imbalanced datasets masks poor precision-recall performance, recommending tracking metrics like F1-score and AUC-ROC vi…
A new paper from researchers at the University of Texas at Austin and Microsoft introduces an execution-free agentic program repair system for enterprise-scale development, achieving a 40% higher fix rate than prior meth…
Kalytera, an AI agent observability platform, automatically evaluates every step of an agent's workflow in real time and surfaces plain-English root causes for failures, catching issues that sampled or after-the-fact ana…
A developer describes how using an AI chat tool transformed their LeetCode practice by eliminating the need to alt-tab between problems and solutions, allowing for more focused and efficient coding sessions.
Orate, a one-time $4.99 purchase, offers on-device neural text-to-speech for Mac using Kokoro for standard voice and Chatterbox for HD voice, processing articles and emails offline from the menu bar without a subscriptio…
A developer demonstrates a practical approach to integrating external APIs with agentic AI, including code examples for weather data and Slack messaging, and emphasizes best practices such as secure API keys, timeout han…
Kimi K3 defeated Anthropic's Claude Opus 4.8 in a head-to-head Three.js coding challenge, scoring 6.5 to 2.1 on a single scored task. The test, judged twice by GPT-5.4 to cancel position bias, found Kimi K3 delivered a r…
A developer used Anthropic's Claude AI to design a custom RISC-V processor, system-on-chip (SoC), and printed circuit board (PCB), demonstrating how large language models can assist in hardware design. The project, docum…
Network expert Glenn Fiedler warned game developers that AI can now find vulnerabilities in game code, urging them to fix security flaws before malicious actors exploit them. Fiedler highlighted that AI tools are increas…
Logitech's G325 LIGHTSPEED gaming headset is available for $39, a 51% discount from its regular price, marking an all-time low. The deal requires promo code LEVEL22 at checkout and features a lightweight design, LIGHTSPE…
An engineer created a minimal AI agent in just 9 lines of Python code, using a custom tool to execute shell commands and a loop that processes user input through a language model. The agent, which calls a remote model en…
Anthropic shipped Record a Skill for Claude Cowork on Pro, Max, and Team plans, turning screen recordings with voice narration into reusable, editable SKILL.md files without requiring any code. The feature runs on macOS,…