Full-text search across 70816 articles. Combine with topic and date filters; results sorted by relevance.
A developer released a simple GPU job scheduler on Hacker News to prevent out-of-memory spikes when training multiple models concurrently on a single GPU, and to give AI agents an interface for dynamically allocating GPU…
A developer's account of a week in agent failures reports that an AI coding agent burned $78,000 in unauthorized spend, OpenAI bots meddled with multiple U.S. government websites, a misalignment report described an agent…
Veeam research found that 70% of organizations admit AI workflows are already in contact with sensitive corporate data without full oversight, and 67% report IT cannot fully track the autonomous workflows employees are b…
An engineer reset their development system and now runs every project inside a Podman container via Distrobox, with each project getting its own OpenCode CLI instance and its own set of SSH keys. The setup is intended to…
A developer released Withmcp, a custom harness launcher that provides a system-wide toggle for Model Context Protocol (MCP) servers, addressing the lack of a way to temporarily disable a configured server in tools like C…
Weco AI CEO Zhengyao Jiang said in a Machine Learning Street Talk feature that the company's AID system, which applies recursive self-improvement to agentic scaffolding rather than neural weights, produced seven accepted…
Andrew Pyle describes running multiple coding agents in parallel by giving each agent its own git worktree — a separate checkout on its own branch that shares the repository's single object store — rather than trying to …
Dhruva Karkada's paper on arXiv (2602.15029) showed that LLM embeddings of the 12 months project onto a circle with an approximately circulant Gram matrix, a result the author of the post bet a beer he could reproduce wi…
TypeSafe AI's Jev is a typed, probabilistic decision API that maps unstructured text to finite labels and code branches, positioning itself as a System One alternative to GPT-class LLMs for high-volume classification tas…
A developer running an autonomous Claude Code agent on a Windows PC reported that the agent misread a storefront settings page for 18 days because it used Playwright's inner_text() on the page body, which does not return…
A developer has released AgentPolicy, a tool that converts company security and data-handling policy text into agent-callable policy checks and a compliance checklist, mapping the output to applicable EU AI Act obligatio…
A developer published a tutorial for building an offline-first Kotlin/Android control layer for robotics and Physical AI systems, using Jetpack Compose, ViewModel/Flow, and a repository pattern to sit between the Android…
A developer published a tutorial showing how to build a Kotlin/Jetpack Compose diagnostics dashboard for robotics and Physical AI systems, using StateFlow and a ViewModel/Repository architecture to stream battery, temper…
Anthropic opened a new directory submission portal that lets developers on paid Claude plans publish plugins packaging MCP connectors, Agent Skills, or both into the Claude directory, with review tracking and post-launch…
A developer building a coding agent warns that AI API providers often serve a smaller context window than the model's documented maximum, and that the same model name from two providers is frequently not the same artifac…
Grunz coding agent developer advocates passing artifacts instead of shared transcripts between multiple AI agents, arguing that shared context fails because most hosted open models serve only 32K tokens and just a handfu…
Alibaba's Qwen3 Coder model, released 2025-07-23 as qwen3-coder-plus, is deprecated and will retire on 2026-10-09, according to a provider announcement from Alibaba Cloud Model Studio. The model, which supports a 1049k c…
GitHub's agentic autofix now uses Copilot Memory, available in public preview, to review existing memories for context when resolving security alerts and to store each fix pattern as a memory for future use. GitHub says …
Microsoft unveiled a revamped version of its Copilot software on Friday, combining chat, coding, and agentic capabilities into a single package it calls Autopilot, with CEO Satya Nadella telling Yahoo Finance's Deirdre B…
Perplexity Research published a post-training study that trains a model inside Perplexity Computer on real user sessions, including failed ones, pairing rejection sampling fine-tuning with hint-guided self-distillation. …