Full-text search across 13179 articles. Combine with topic and date filters; results sorted by relevance.
A developer published a hands-on walkthrough for building generative AI agents on AWS using Amazon Bedrock for models, Strands Agents for agent code, and Amazon Bedrock AgentCore for cloud deployment. The guide covers ac…
OpenAI reported on October 19 that its GPT-6.1 Sol model correctly migrated 97.9% of COBOL programs in the company's own migration evaluation, up from 5.4% for the previous-generation GPT-5.6 Sol. At low reasoning effort…
A hands-on guide demonstrates running the Swiss-made Apertus 1.5 8B multimodal model on a single Nvidia RTX A6000 with 48GB of VRAM using the vLLM inference framework, requiring at least 32GB of GPU VRAM in BF16. The aut…
ZizkaDB published a guide showing Cursor users how to connect its Model Context Protocol server to break down token costs by model, session and step. The setup takes about 30 seconds via uvx, using either the self-hosted…
An open-source toolkit called pdd-kit, installed via `npx pdd-toolkit install`, introduces Product-Driven Development (PDD) to give coding agents and humans a single git-tracked product model stored in a `product-model/`…
A developer demonstrated that Neon's API-first design lets coding agents like Claude Code build missing features directly against its REST API rather than waiting for a polished UI. Pointing the agent at Neon's documente…
A developer's roundup of eight blog posts examines practical lessons from running Claude Code, covering how its rolling 5-hour and weekly quotas are metered, the cost trap of the built-in Explore subagent defaulting to t…
Developer Luís Rudge released Omasharp, an open-source toolkit that lets developers build Omarchy desktop apps in C# and QML, installed via `dotnet new install Omasharp.Templates`. In a benchmark of Omarchy's C++ calcula…
Meta launched its Muse personal AI agent app in the US on September 8, and it was downloaded more than 2.5 million times within a couple of weeks, briefly topping the Apple App Store charts. Meta's team, led by Alexander…
Gradium open-sourced Phonon, a family of 31m and 40m parameter on-device text-to-speech models, with the English Phonon 31m released under Apache 2.0 and the 40m model under CC BY-NC. Phonon 31m starts speaking in 7 ms o…
Databricks moved its CustomerLake Campaign Agents into Beta and opened Profile Agents in Private Preview, expanding the Agentic CDP embedded in its data and AI platform to more customers. HP's Global Head of Marketing Te…
OpenCode disclosed on October 16, 2026 that an intruder accessed a legacy system tied to OpenCode Console, its hosted service for managing AI coding workflows, potentially exposing third-party provider API keys for OpenA…
Google DeepMind reported that four Gemini 4 Argon agents autonomously completed Minecraft, defeating the Ender Dragon in 27 hours and 14 minutes without assigned roles or human-written game logic, coordinating through in…
Microsoft on October 19 announced an expansion of Project Perception that treats internal AI agents as insiders requiring continuous supervision and adaptive containment, with components including Guardian Agents, Dynami…
OWASP's Top 10 for Agentic Applications for 2026 now lists Agentic Supply Chain Vulnerabilities (ASI04), covering risks that arise when third-party agents, tools and artifacts are malicious, compromised or tampered with …
A developer audited eight memory-layer tools for AI coding agents as of October 2026, comparing GitHub stars, pricing, self-hosting support and autonomous memory-writing, then built a ninth, MaxGraph, a self-hosted serve…
The open-source project STROT is promoting an architecture that uses a large language model once to compile a bounded decision task, then runs a smaller local decision model per record instead of calling a hosted LLM for…
Sanity shipped four new tools to its Sanity MCP server in October that let AI agents upload images and files into a dataset or Media Library from public URLs, local files, or ChatGPT web attachments, closing a gap where …
CacheVerifier launched a Python client for its hosted API that approves or rejects semantic-cache hits before an application serves a cached answer, aimed at catching similarity matches that are close but wrong. The clie…
Developer iha2 released superlite, an open-source Claude Code plugin that plans a build, splits it into parallel tasks, routes each task to the cheapest capable agent, and reviews the result without the human approval ga…