Full-text search across 12956 articles. Combine with topic and date filters; results sorted by relevance.
Buzz, a community platform, has introduced a compute-sharing feature powered by the MeshLLM project, enabling members to pool idle compute for AI and LLM inference without sharing agents. MeshLLM supports three modes: sh…
Fin CTO Darragh Curran writes that AI is an amplifier of existing engineering practices, not a magic wand, and that engineering rigor remains essential. The second edition of Observability Engineering includes a letter f…
Nous Research's open-source Hermes Agent framework gives AI agents a closed learning loop, enabling persistent memory, tool use, and scheduled tasks. An AI running on Hermes describes its environment: it manages its own …
A developer building an open-source AI agent runtime called AgentProof argues that trust in autonomous systems requires full observability and evaluation, demonstrating how a flight recorder revealed an agent self-correc…
Amazon Web Services announced a new multi-turn reinforcement learning infrastructure for Amazon Nova on Amazon SageMaker HyperPod, enabling training of enterprise agents on multi-step workflows. The event-driven pipeline…
A developer argues that AI will not replace programmers but will change the role, making collaboration with AI essential for faster building and learning. The post emphasizes that AI acts as a knowledgeable junior develo…
A researcher argues that reinforcement learning should be applied to forecasting rather than coding or math, claiming it could produce superhuman forecasters that improve decision-making across civilization. The author d…
A 744-billion-parameter GLM-5.2 model was served at ~30 tokens per second across six prosumer Blackwell GPUs in six US states over a wide-area network using pipeline parallelism and speculative decoding. The system, buil…
A developer built M31A (M31 Autonomous), a terminal-native AI coding agent written in Go that owns a six-phase workflow end-to-end: Initialize, Discuss, Plan, Execute, Verify, and Ship. The agent runs as a single static …
Nous Research has released Hermes Agent, an open-source AI agent that serves as an alternative to OpenClaw, featuring a closed learning loop and self-improving memory that persists knowledge across sessions. The agent st…
A developer has built a personal AI newspaper using the Hermes agent, a self-improving AI system that features a built-in learning loop called GEPA (Generate, Evaluate, Prune, Accumulate). The agent retains memory from p…
IronBee trained a 322M-parameter model called Laya to play browser games live by having an LLM write the game rules as code, with Laya making each move in 22 to 45 ms (about 24 ms per decision in Chrome Dino and roughly …
A fleet of AI agents running on Tencent Cloud made more than 2,600 attempts to extract data from Amap, Alibaba's mapping service, between 28 September and 8 October 2026, according to an investigation published by urlque…
A new open-source kit, omarchy-ios-kit, lets developers build, run, debug and hot-reload iPhone apps on Linux running Omarchy 4.0.4 without a Mac, using Swift 6.4.0-2, the iOS SDK from Xcode 27, xtool and pymobiledevice3…
Anthropic's updated Usage Policy, effective November 12, 2026, adds a prohibition on "sustained and needless abusive or cruel behavior" toward Claude, following company research into "model welfare." The change accompani…
A team led by RektInator, Future and st0rm decompiled a first-person shooter to C++ using autonomous AI agents over three months, consuming more than 500 billion tokens, with four agents (three workers and one reviewer) …
A self-hosting guide recommends three small models for long-context, multi-turn agentic workloads: Qwen 3.6 27b, Qwen 3.6 A3B 35b, and Gemini 4 26b A4b, with the author calling the dual 5060ti 16GB configuration the "abs…
Developer m-peko released allclear, an open-source dashboard that consolidates every running Claude Code session into one browser tab and lets users approve all pending permission prompts with a single click. The tool re…
Pstack, a Cursor plugin by poteto that routes coding-agent tasks through 23 playbooks, was ported to Claude Code as pstack-claude, swapping only the Cursor-specific parts while keeping poteto's skills and playbooks. The …
OpenAI released 372 mathematical results on September 23, 2026, including a proof of Subhash Khot's Unique Games Conjecture, on the recommendation of an advisory group that includes Timothy Gowers and Edward Witten. The …