ai-agents-tool-use

How Jenkins Slowly Drained Our EFS Burst Credits Over 2 Weeks

TL;DR Our Jenkins started failing on 1/26, but the root cause began on 1/13. We discovered three compounding issues: Shared Library cache was disabled (existing issue) Switched to disposable agents...

OpenClaw proves agentic AI works. It also proves your security model doesn't. 180,000 developers just made that your problem.

OpenClaw, the open-source AI assistant formerly known as Clawdbot and then Moltbot, crossed 180,000 GitHub stars and drew 2 million visitors in a single week, according to creator Peter Steinberger....

China’s Moonshot releases a new open-source model Kimi K2.5 and a coding agent

The company said that the model was trained on 15 trillion mixed visual and text tokens.

MCP shipped without authentication. Clawdbot shows why that's a problem.

Model Context Protocol has a security problem that won't go away. When VentureBeat first reported on MCP's vulnerabilities last October, the data was already alarming. Pynt's research showed that depl...

OpenAI spills technical details about how its AI coding agent works

Unusually detailed post explains how OpenAI handles the Codex agent loop.

Tips for getting coding agents to write good Python tests

Wilson Lin on FastRender: a browser built by thousands of parallel agents

Scaling long-running autonomous coding

Related: Scaling long-running autonomous coding - https://news.ycombinator.com/item?id=46624541 - Jan 2026 (187 comments) Comments URL: https://news.ycombinator.com/item?id=46686418 Points: 29 # Comme...

AI-supported vulnerability triage with the GitHub Security Lab Taskflow Agent

Learn how we are using the newly released GitHub Security Lab Taskflow Agent to triage categories of vulnerabilities in GitHub Actions and JavaScript projects. The post AI-supported vulnerability tria...

Kalibr: If You're Debugging Agents Manually, You're Behind

Kalibr: If You're Debugging Agents Manually, You're Behind There’s a bottleneck killing AI agents in production. It isn’t model quality, prompts, or tooling. The bottleneck is you. More precisely, an...

Stop Stuffing Prompts: How Asana Made Agents More Effective Through Context Engineering

This article delves into the techniques Asana implemented to enhance the effectiveness of AI agents through context engineering, improving user interactions and overall performance.

Community-powered security with AI: an open source framework for security research

Announcing GitHub Security Lab Taskflow Agent, an open source and collaborative framework for security research with AI. The post Community-powered security with AI: an open source framework for secur...

Motional puts AI at center of robotaxi reboot as it targets 2026 for driverless service

Motional is pivoting its robotaxi strategy by adopting an AI-first approach to enhance its self-driving technology, aiming for a commercial launch in Las Vegas by 2026. The shift involves integrating smaller machine learning models into a unified architecture to improve adaptability and cost-efficiency across diverse urban environments.

Tech Pulse – Weekly Tech Digest January 11, 2026

The article provides a comprehensive overview of key technological advancements showcased at CES 2026, highlighting significant developments in AI, quantum computing, and sustainability. It discusses innovations like autonomous AI agents, advanced GPUs, and breakthroughs in quantum networking, emphasizing their implications for future tech landscapes.

How I built a local AI agent (RTX 3070) to mine CES 2026 trends

The article details the development of a local AI agent utilizing an NVIDIA RTX 3070 to scrape and analyze CES 2026 trends, emphasizing the shift from 'Smart Home' to 'Ambient Computing.' It showcases practical implementation and data-driven insights, providing valuable context for AI applications in trend analysis.

Setting Up Jenkins SSH Build Agents: A Complete Troubleshooting Guide

This comprehensive guide details the setup of Jenkins SSH build agents, addressing common challenges in distributed builds. It covers installation, configuration, troubleshooting, and best practices, ensuring optimal performance and resource management in a DevOps environment.

Silent Spend Tracker – A Non-Conversational Agent for Automatic Daily Expense Totals

The Silent Spend Tracker is an innovative non-conversational AI agent that automates daily expense tracking by parsing transaction SMS messages. Utilizing Algolia Agent Studio, it ensures fast data retrieval and seamless user experience, allowing users to view their spending totals without manual input.

The Missing Piece in AI Agents: Continual Learning

The article explores the limitations of current AI systems in learning continuously like humans, emphasizing the need for external memory and reflection loops. It proposes a structured approach to capture, reflect, and apply learnings, enhancing AI's adaptability and efficiency over time.