Full-text search across 68293 articles. Combine with topic and date filters; results sorted by relevance.
A developer's decentralized multi-agent protocol, IRC-A, successfully handled a live production query about July sales, returning real data from a real database within 46 minutes of adding a new sales-reports agent. The …
Claude 3 Opus is too slow and expensive for simple coding tasks, according to a developer's experience; Claude 3.5 Sonnet completes the same refactoring in 12 seconds versus 15-30 seconds for Opus, at $3/$15 per million …
Meta Platforms Inc. released Muse Glimmer, a 30-billion-parameter open-source AI model designed for local agentic workflows on consumer hardware, on August 10, alongside a manifesto by CEO Mark Zuckerberg arguing for wid…
Alibaba released Qwen3.8-27B, a dense multimodal model with open weights under Apache 2.0, which outperforms Meta's Muse Glimmer 30B on every benchmark where both were tested, including a 73.0 vs 51.7 score on Terminal B…
A developer describes how AI agents have transformed their daily work as a tech lead, shifting focus from writing code to designing processes and making judgment calls. They built a stack of scheduled agents that brief t…
Hugging Face reported that coding agents fully reproduced every extracted claim in 266 of 2,226 ICML 2026 papers, with 632 more showing partial evidence and no falsified claims. The 19-day challenge, which ran from July …
A new open-source macOS menu bar app, usagent, tracks Claude subscription usage by displaying the closer of the 5-hour rolling window or weekly cap, with percent used and time to reset. Built by reverse-engineering an un…
Apertus, a Swiss AI initiative, misrepresents its 'open' status by conflating technical accessibility with legal freedom, according to a technical audit. The audit found that while Apertus's model weights and code are op…
A developer's AI lead-qualifying agent built on n8n and llama-4-scout through fal caught a prompt injection 5 out of 5 times but was fooled by a contradictory lead claiming a 3-person company had 200 employees, returning…
A developer has written a two-book series on AI-assisted development, arguing that developers should build and understand fundamentals before using AI tools. The books, covering frontend and backend development, delibera…
ParleHub launched today on Product Hunt, offering enterprises a platform that ties AI usage to client projects with shared threads, project-specific budgets, and expense codes, while integrating with Microsoft Entra ID a…
OpenAI has released a preview of its ChatGPT desktop application for Linux, an Electron-based proprietary program that supports Ubuntu 24.04 LTS and 26.04 LTS, Debian 13, and Fedora 43 and 44 on x86-64 and Arm64. The app…
Mirage, the AI startup behind the video-editing app Captions, launched a 24-hour AI-generated news channel called Mirage News Network, which reached 50,000 viewers on X and drew 824,000 impressions on its livestream post…
Syntaf released hop v0.1.0, a CLI tool that searches all git repositories under a user's code directory and jumps to the worktree holding a given branch, with tiered matching, tab completion, and an installer that config…
Ken Koon Wong, in a blog post published August 5, 2026, coded K-Fold cross-validation from scratch in R and found that at n=1000, leave-one-out cross-validation (LOOCV) has lower bias but higher variance than 10-fold and…
A developer shared a detailed CLAUDE.md configuration file for an iOS app called Trailmark, which is backed by a Node.js REST API. The file establishes strict coding rules, including type safety, naming conventions, and …
A solo founder shipped 128 releases of an SDLC orchestrator for AI coding agents that never gained a single external user, then built a second product with 442 passing tests that broke in real use, according to a retrosp…
DeepSeek is recruiting researchers, engineers, and product staff for an Agent Harness team in Beijing and Hangzhou, according to its hiring page and reports from May 20–21, 2026. The roles focus on context management, me…
DeepSeek V4 Pro 0813, released by DeepSeek without a launch event, scored 87.9 on Terminal Bench 2.1, up from 72.1 in its April preview, and topped Cyberjim (83.3) and Automation Bench (31.8) among rivals. Independent te…
Cynative, an open-source infrastructure security deep research agent, uses a two-sided architecture—a sandbox and an action-gate—to ensure AI agents cannot escape their trust boundary, granting read-only access by constr…