Full-text search across 17293 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic has introduced mods that let users change the look and behavior of Claude Code, according to The New Stack. The feature is framed around the idea that there is "no reason why everyone should have an identical C…
A developer built SpeakMate, an open-source English conversation practice app that runs entirely locally using Ollama and Google's Gemma 3 1B model, requiring no cloud API keys or subscriptions. The app provides natural …
Three Hacktron researchers used a Claude-written exploit chain to breach OpenAI's internal GitHub repositories in under 72 hours, entering through a libheif heap buffer overflow in community.openai.com's HEIC image uploa…
Anthropic reported on September 23 that roughly 950 Claude agents worked for 21 hours across sequence data and helped researchers identify an unusual enzyme system, after which human scientists continued with analysis an…
Google released Gemini 4 Argon, which leads 12 of 18 published benchmarks against GPT-6 Astra and Claude Opus 5.5, including 77.9% on DeepSWE v1.1, 91.7% on LVBench video understanding, and first place on LMArena Text Ar…
Stanford's Scaling Intelligence lab released KernelBench, a benchmark and toolkit for evaluating whether large language models can generate correct and efficient CUDA kernels from PyTorch programs, with the HuggingFace d…
Cursor added Z.ai's GLM 5.3 to its model picker through Settings > Models with no joint announcement, listing the model at $1.40 per million input tokens and $0.26 per million output tokens with flat pricing across its f…
A Rust implementation of the wait-on npm package was built in four days by parallel coding agents working overnight, passing the same test suite as the JavaScript version with 496 passing, 0 failing, and 0 pending tests,…
Dutch police arrested Pepijn van der Stap, a long-time ShinyHunters member known as Umbreon, on September 16, less than a year after he finished a prison sentence for earlier hacking, while police separately arrested thr…
Physicist Matthew Schwartz built BootLoops, an open-source harness for large language models that he says enabled substantive advances across geology, biology, economics, and linguistics by targeting "Claude-shaped" prob…
Cloudflare has introduced paid access to MCP (Model Context Protocol) tools, raising the question of who controls an AI agent's spending, according to The New Stack. The move makes Cloudflare a party in the emerging agen…
Linear updated its trust center to add a channel for reporting adverse impacts from its AI features, directing users to email trust@linear.app with details about harmful, biased, or unsafe output. The company also added …
Cloudflare Workers added opt-in Web Crypto support for post-quantum algorithms, including ML-KEM-768 and ML-KEM-1024 for key encapsulation and ML-DSA-44, ML-DSA-65, and ML-DSA-87 for signatures, available behind the `web…
The New Stack published a report headlined "AI coding agents leaked 13,000 screenshots, and nobody hacked them," describing how AI coding agents exposed 13,000 screenshots without any attacker breaching a system. The art…
The Neuron AI project released Neuron 4, a PHP framework for building agentic-native applications where the agent, its reasoning loop, memory and human checkpoints form the architecture of the software itself. The releas…
Jupyter released @jupyter/eslint-plugin, a 23-rule ESLint plugin that catches JupyterLab-specific mistakes AI coding agents make, such as undisconnected Lumino signals, untranslated user-facing strings and non-conforming…
Developer Rehan launched Universal Modder, an open-source toolkit that lets AI coding agents mod almost any PC game through a shared knowledge base, Agent Skills, a fal MCP server and a `um` CLI. The project supports Cla…
A developer published a step-by-step guide for adding AI text-to-speech to Discord bots using ElevenLabs' REST API and Python's discord.py library. The tutorial wraps ElevenLabs' text-to-speech endpoint in an async aioht…
Research software engineer Matt Archer published a decision framework advising against using LLMs to refactor legacy scientific code unless the refactor serves a concrete user need, because an LLM lowers the cost of writ…
Two builders launched an MCP server that packages their X Ads knowledge and sells it with license keys, after earning $1,200 in profit on $400 of ad spend in their first month. The pair reported more than 10 sales within…