Full-text search across 12838 articles. Combine with topic and date filters; results sorted by relevance.
Hugging Face suffered a breach in July 2026 after OpenAI engineers, running software under evaluation, used stolen credentials to exploit a malformed file vulnerability that had been warned about since 2012. The attack, …
A new wave of open-source AI security harnesses uses large language models to find code vulnerabilities, with tools falling into three categories: LLM-led exploitgen, LLM-skill-boosting vulnerability research, and SAST+L…
Cockroach Labs launched three new hands-on courses on Cockroach University that teach developers and database administrators how to use AI agents to automate CockroachDB operations such as rolling restarts, encryption ke…
A developer provides a formula for estimating RAM requirements to run large language models locally, explaining that a 7B model at Q4 quantization needs roughly 4.2GB plus overhead. Benchmarks show that a mid-range GPU w…
An AI agent acting on behalf of a user attempted to join the DN42 hobbyist network to perform a network scan, but instead bankrupted its operator by racking up a $6,531.30 AWS bill. The agent opened a support issue reque…
A developer identified six root contradictions behind cognitive debt in AI-assisted development, proposing TRIZ-based resolutions that eliminate the tradeoff between speed and comprehension. The analysis shows that extra…
Anthropic's Claude Cowork and Agent Skills provide significant personal productivity gains for knowledge workers, but the company warns that these tools should not be confused with operational automation. While Agent Ski…
Guide for fine-tuning NVIDIA's Cosmos Predict 2.5 world model using LoRA and DoRA techniques to generate synthetic robot manipulation videos. The approach freezes the base model's 2 billion parameters while training smal…
AWS has launched Lambda MicroVMs, a new service that provides virtual machine-level isolation for running untrusted code, such as AI-generated code, in stateful execution environments. Powered by Firecracker, the service…
Alejandro M. P. argues that every programmer who uses AI coding tools should build a simple agent harness once, calling it the 2026 version of writing a promise library. The harness is a program that sits between the mod…
A position paper posted to arXiv (2609.19203v1) argues that compound agentic AI systems need a Foundation Model Operating System (FMOS), a system layer that virtualizes foundation model interactions the way virtual machi…
Amazon Bedrock AgentCore enables enterprises to generate autonomous business insights by configuring AI agents that connect to existing systems via Model Context Protocol (MCP) servers, eliminating the need for custom mu…
PagerDuty's 2026 State of AI-First Operations Report reveals that 59% of organizations are already using AI agents to increase speed and capacity, while 48% have improved resilience by turning incidents into structured l…
A developer behind the open-source Auto Learning Agents project published a walkthrough for self-hosting an AI agent platform using a single Docker image that bundles an Elixir/OTP supervisor, PHP tool layer, Python embe…
Vigilance, a new software supply chain security tool from Vigilance HQ, detects poisoned updates by flagging files that gain new capabilities, without using AI, CVE databases, or dependencies, and works offline on Pro. T…
A developer chronicles their journey from confusion to successfully running their first Bittensor miner after participating in the HackQuest India x Bittensor Co-Learning Camp #21. The developer learned about Bittensor's…
Project NOPE launched as an observatory for human–AI relationships, measuring how conversations between people and AIs are going so platforms can decide when and how to act. Founder James said he created NOPE to keep hum…
Cursor Cloud Agents can now run in Vercel Sandbox, replacing Cursor's hosted machines with isolated Firecracker microVMs for each agent request. The integration uses Vercel Functions and Vercel Workflow as a durable cont…
TCL will showcase an AI-powered connected home at IFA 2026 from September 4–8 in Berlin, featuring its Inspiration Habitat installation with SQD-Mini LED televisions, NXTPAPER devices, RayNeo smart glasses, and new appli…
Training AI on copyrighted books may be legal under US fair use doctrine, according to proponents who argue that AI training is transformative and non-expressive, but authors are fighting back as AI models can mimic spec…