Full-text search across 70231 articles. Combine with topic and date filters; results sorted by relevance.
Researchers at Kaspersky have discovered malware hidden in Wallpaper Engine workshop uploads on Steam that can steal Steam login credentials. The campaign, active since late 2025, primarily targets gamers in China and Ru…
A developer released Avera, an open-source tool that deterministically detects introduced regressions by comparing baseline and current test runs, blocking releases only when a previously passing test fails. The tool pro…
Amazon made the managed agent harness in Amazon Bedrock AgentCore generally available at AWS Summit New York on June 17, enabling developers to deploy production-grade AI agents using a config file instead of custom orch…
A developer built PyCodeIt, a free Python coding challenge platform that generates unique problems using a Bring Your Own Key (BYOK) architecture with Groq and Supabase. The platform keeps server costs at zero by routing…
A developer built a selector-free web scraper using Opticparse, an AI-powered tool that captures webpage screenshots and uses Gemini's multimodal vision to extract structured JSON data. The scraper bypasses dynamic CSS c…
Researchers have developed a method called Emergent Alignment that enables large language models to self-correct unethical outputs by adding a conscience step and using Direct Preference Optimization. The technique works…
Amendor launches a tool that lets website users request changes by clicking on a live site and describing what to modify. A coding agent automatically implements the change, creates a pull request, and generates a previe…
SpaceX went public on June 12, 2026, in the largest IPO in history, raising up to $86 billion and achieving a valuation between $1.75 trillion and $2 trillion. Four days later, the company spent $60 billion to acquire AI…
DigitalOcean published a tutorial on June 18, 2026 presenting a hybrid inference pattern that splits AI workloads between local hardware and serverless inference, offering a decision framework for cost, latency, and data…
A developer demonstrates using Cosmic, a structured, versioned, API-accessible object store, as the memory layer for AI agents. The approach stores agent messages, system prompts, findings, and instructions as versioned …
A new free eBook titled 'Building Pragmatic AI Agents That Use Tools and APIs' provides a practical guide to constructing production-grade AI agents, covering five frameworks including DSPy and OpenAI Agents SDK. The boo…
Microsoft warns developers that overloading AI coding agents with redundant documentation wastes tokens and degrades performance. The company advises measuring baseline model knowledge first, then building lean skills th…
Cajal (YC W26) released Talos, an open-source WebAssembly interpreter and formal verification framework built in Lean, enabling mathematical proofs of correctness for Wasm modules. The tool targets AI-generated code and …
Higgsfield, a San Francisco AI video startup, has reached a $500 million revenue run rate, up from $50 million last September, and is cash-flow positive. The company aims to rival AI coding platforms like Cursor and Lova…
Z.ai released GLM-5.2, an open-weight model that the author calls the best open-weight model available. The model introduces IndexShare, a cross-layer reuse trick for DeepSeek Sparse Attention that reduces the cost of 1M…
Researchers introduced PROPEL, a framework that trains task generators for reinforcement learning by using a lightweight activation probe to predict solver pass rates, avoiding costly solver rollouts. In tests on math, c…
Researchers from Hao AI Lab introduced JetFlow, a speculative decoding framework that breaks the scaling ceiling of autoregressive LLMs by combining one-forward drafting efficiency with branch-wise causal conditioning. J…
Draft, an open-source tool for AI agent context synchronization and collaboration, was released on Hacker News. It automatically syncs context edits from agent sessions, Slack threads, and notes to a shared Git repo, wit…
Vlk, a native MCP server, provides persistent working memory for IDE coding agents by exposing a single tool, vlk_time_travel, that prunes dead memory slots from SQLite and injects learned lessons. This enables agents to…
A developer has released Relego, a free, self-hostable alternative to Readwise that allows users to upload Kindle highlights and receive daily or weekly recaps via Kindle or email. Built with .NET and AI assistance, the …