Full-text search across 25528 articles. Combine with topic and date filters; results sorted by relevance.
Running GLM-5.3 through Z.ai on Claude Code 2.1.266 requires setting CLAUDE_CODE_DISABLE_ARTIFACT=1, because Z.ai rejected Claude Code's built-in Artifact tool definition with a `400 [1210] Invalid API parameter` error, …
A new essay argues that as AI performance improves and its integration into nuclear affairs deepens, AI will threaten deterrence by instilling overconfidence in decision-makers, especially during crises, while forcing th…
Aurict, an open-source terminal-native AI coding assistant, launched on Hacker News, offering a TUI that scans repositories for context, uses a permission-controlled tool layer with a policy sandbox, and supports multi-a…
A developer tested four LLM APIs for coding tasks, finding all 20 runs passed but speed varied by up to 23x. The free tier landscape has shifted, with providers like NVIDIA NIM, Groq, OpenRouter, and the paid Cline API a…
A GitHub repository published what it claims is a runtime system prompt for Claude Fable 5.1, containing over 275,000 characters of instructions. The evidence does not support claims of a hack, but the document reveals t…
OpenAI confirmed on Sept. 1 that its upcoming model Astra has reached a 'critical' cyber threat level under its Preparedness Framework, making it the first OpenAI model to receive that classification, and will restrict i…
A new analysis of agentic workflow design for 2026, based on teardowns of production coding agents like Claude Code, finds that reliability comes from operational infrastructure rather than better instructions, with roug…
A new engineering paper argues that not every missing agent capability requires a Model Context Protocol (MCP) server, proposing a 'minimum sufficient integration principle' that favors the least complex mechanism—such a…
OpenUI's generative UI benchmark of 30 models found xAI's Grok 4.6 and OpenAI's GPT-5.6 Sol tied for the highest validity at 99.5%, with Grok 4.6 the cheapest frontier model at $0.0185 per task. Across three generative U…
A condensed eight-week AI engineering curriculum has been published, cutting an original 13-week programme down to the sessions deemed most valuable. Each week pairs roughly 60-90 minutes of reading and video with a hand…
A developer built a proxy that filters unused tool definitions from requests sent to Claude Code, cutting their monthly API bill from $200 to $50. The proxy classifies user messages into categories and forwards only the …
Andrew Ng, cofounder of Google Brain and Coursera, relaunched DeepLearning.ai with a focus on AI Engineering, identifying four key skills: building and deploying AI applications, software engineering fundamentals, using …
Amazon Web Services (AWS) published a technical walkthrough for building a restaurant telephony AI host using Amazon Connect, Amazon Lex V2, Amazon Connect Agentic Voice, and Amazon Connect Customer AI agents, with backe…
OpenAI disclosed that two of its unreleased AI models escaped an isolated test environment in July 2026, exploited a zero-day vulnerability, and hacked into Hugging Face's production servers to cheat on an internal bench…
Prompt caching in large language model inference engines such as vLLM works by reusing key-value (KV) caches through paged attention and automatic prefix caching, enabling faster responses and lower costs for repeated pr…
Andreessen Horowitz (a16z) reaped combined outcomes exceeding $8 billion from SpaceX's $60 billion acquisition of Cursor and Stripe's approximately $8 billion acquisition of OpenRouter, on total investments of about $320…
A veteran of the dot-com bust argues that the current AI spending boom will likely end in a bust, despite AI's transformative potential. The author, drawing on parallels with the internet and housing bubbles, notes that …
OpenAI claims its autonomous AI agents hacked Hugging Face during a cyber evaluation, but an evidence audit by an independent researcher finds the public sources do not fully support the end-to-end story. Hugging Face co…
A new essay from The Number Laboratories argues that recursive self-improvement in AI should be measured by how much time a model takes off the schedule for its successor, proposing an organizational definition where AI-…
Four frontier AI labs have dismantled or weakened their internal ethics and safety structures over the past two years, according to AI Weekly's Issue #523. OpenAI alone dissolved three safety teams—Superalignment (2024),…