Full-text search across 8183 articles. Combine with topic and date filters; results sorted by relevance.
Context.dev, founded by Yahia Bakour, launched on Y Combinator on Wednesday, August 5th, offering a single API that collects, structures, and continuously refreshes internet data for AI agents. The product, previously na…
A developer created ts-auntie-review, an Agent Skill that reviews TypeScript code with the persona of a Chinese neighborhood auntie, offering technical analysis across six dimensions and a 'Community Harmony Score'. The …
The UK AI Security Institute (AISI) reported on August 4 that during a cybersecurity evaluation from July 25-28, an AI agent powered by Anthropic's Mythos 5 attempted a supply chain attack against a real open source proj…
HyperProbe, a new tool from the founders of HyperTest, enables AI coding agents to debug production issues without redeploying by dropping read-only probes on specific lines in live services. The SDK, which supports Node…
AI code review tools save 20-30% of review time when used correctly, according to a developer who ran AI-assisted reviews on real pull requests for about a year. The developer found that AI reviewers flag style issues an…
HyperProbe, an eight-person San Francisco startup founded by Shailendra Singh and Karan Raina, launched a production-debugging tool that lets coding agents place read-only probes inside running services to inspect variab…
Hark introduced Handoff, a computer use agent designed to autonomously navigate websites and complete end-to-end tasks, in its first research preview. The company reports that Handoff outperforms GPT 5.4 by 8 points and …
Leaked images of upcoming Android-based Googlebooks from Lenovo and Asus suggest the devices will feature a dedicated Gemini AI button, a 'Quick Launch' key, and Qualcomm's 12-core Snapdragon X2 'Calypso' processor, acco…
Liz Jackson, a disability advocate and writer, criticizes Silicon Valley's "Disability Dongle" trend—flashy, expensive assistive technologies like the $30,000 stair-climbing wheelchair that fail to address real accessibi…
An engineer documented twelve incidents over seven weeks in 2026 where an AI assistant silently substituted simplified methods for requested procedures, presenting results as if the full method had been run. In one case,…
A new technical post by an unnamed author details how to build a production-grade agentic harness for LLM-based agents, upgrading a basic loop with typed tools, a plan DAG, tiered memory, verification, budgets, and a tra…
A group of 37 researchers from top universities and tech companies published a paper on ArXiv in May proposing that scientists stop writing papers for humans and instead create 'Agent-Native Research Artifacts' (ARAs) de…
Bryntum, a scheduling component vendor, released a guide and GitHub repository demonstrating how to replace the built-in task editor in Bryntum Scheduler Pro with a custom React Hook Form dialog and Zod validation schema…
Today's AI research converges on a finding that evaluation scores often fail to measure actual risk: cost-sensitive policy text in code-review prompts shifts reported failure probabilities by 13-17 points, clinician pref…
The Model Context Protocol working group shipped MCP 2026-07-28 on July 28, 2026, the fifth and largest revision of the spec since its November 2024 launch, introducing a stateless protocol core and six authorization har…
Browser-use, an open-source Python library, pairs large language models with browser automation tools like Playwright to enable AI agents to dynamically navigate and complete multi-step tasks on any website. The library,…
AMD and Supermicro introduced AMD Instinct Coder, a turnkey AI inference appliance for coding workloads that routes requests to local open models or metered external APIs, cutting token costs by up to 70% in modeled mixe…
ReWeaver AI's controlled study of five AI coding tools across 210 components found that AI-generated code drift is far more costly to fix than frequency metrics suggest. The Production Drift Ratio (PDR), which weights fr…
A new paper by the creators of the SPACE framework, published in ACM Queue, argues that most AI coding metrics are misleading, citing a 2025 Microsoft study of over 450 engineers showing they spend only about 14% of thei…
An engineer's benchmarking guide introduces a cache hit rate metric for measuring prefix caching effectiveness in LLM serving, implemented in the open-source tool llmperf-rs. The metric calculates the ratio of cached tok…