Software development
Software development

Software development

The AI Revolution in Development: Why Outer Loop Agents Are the Next Big Thing

Agentic AI Patterns Reinforce Engineering Discipline

Agentic AI patterns enhance engineering discipline and adapt established practices for AI-assisted software development.

fromGeorge London

Software development

AI Agents Could Make Free Software Matter Again, George London

fromSitePoint Forums | Web Development & Design Community

I Built a Desktop Multi-Agent System.Conceptually Goes Beyond Codex Desktop and Claude Code Desktop

A new open-source project enables the creation of customizable AI agent teams for various tasks and workflows.

fromwww.sitepoint.com

I Built a Desktop Multi-Agent System That Outperforms Codex and Claude Code

A new open-source project enables the creation of customizable AI swarms for collaborative tasks across various industries.

fromApp Developer Magazine

11 hours ago

What can you build with ChatGPT in 48 hours

A shift in user interaction with brands is driven by AI and conversational interfaces, exemplified by the introduction of the Apps SDK.

The AI Revolution in Development: Why Outer Loop Agents Are the Next Big Thing

AI is set to revolutionize post-code push processes, automating tasks like security fixes, error logging, and code reviews.

Agentic AI Patterns Reinforce Engineering Discipline

Agentic AI patterns enhance engineering discipline and adapt established practices for AI-assisted software development.

fromGeorge London

AI Agents Could Make Free Software Matter Again, George London

AI coding agents may significantly enhance the relevance of free software by enabling more users to modify and share code.

fromSitePoint Forums | Web Development & Design Community

I Built a Desktop Multi-Agent System.Conceptually Goes Beyond Codex Desktop and Claude Code Desktop

A new open-source project enables the creation of customizable AI agent teams for various tasks and workflows.

fromwww.sitepoint.com

I Built a Desktop Multi-Agent System That Outperforms Codex and Claude Code

A new open-source project enables the creation of customizable AI swarms for collaborative tasks across various industries.

Cursor updates its platform with a focus on autonomous AI agents

Cursor 3 enhances software development by integrating AI agents for collaborative coding, reducing manual programming and streamlining workflows.

Running your life from terminal is peak 2026 - and that's not the flex you think it is

Claude Code transforms personal and professional workflows through automation and task management, enabling users to save time and prioritize effectively.

Here's what that Claude Code source leak reveals about Anthropic's plans

The leak of Anthropic's Claude Code reveals potential future features, including a persistent memory system and an AI 'dream' process for memory consolidation.

Anthropic admits Claude Code quotas running out too fast

Users of Claude Code are facing high token usage and early quota exhaustion, disrupting their coding work.

Anthropic accidentally exposes Claude Code source code

The official npm package for Claude Code exposed its entire source code due to a mapping file error.

Entire Claude Code CLI source code leaks thanks to exposed map file

Claude Code's complexity and architecture provide valuable insights for competitors and pose security risks for Anthropic.

Claude Code Memory 2.0

Claude Code memory enhances performance by providing persistent context for better decision-making across interactions.

11 hours ago

Running your life from terminal is peak 2026 - and that's not the flex you think it is

Claude Code transforms personal and professional workflows through automation and task management, enabling users to save time and prioritize effectively.

Here's what that Claude Code source leak reveals about Anthropic's plans

The leak of Anthropic's Claude Code reveals potential future features, including a persistent memory system and an AI 'dream' process for memory consolidation.

Anthropic admits Claude Code quotas running out too fast

Users of Claude Code are facing high token usage and early quota exhaustion, disrupting their coding work.

Anthropic accidentally exposes Claude Code source code

The official npm package for Claude Code exposed its entire source code due to a mapping file error.

Entire Claude Code CLI source code leaks thanks to exposed map file

Claude Code's complexity and architecture provide valuable insights for competitors and pose security risks for Anthropic.

Claude Code Memory 2.0

Claude Code memory enhances performance by providing persistent context for better decision-making across interactions.

more#claude-code

5 hours ago

I saved a doomed Windows laptop by embracing Linux

The solution, according to Microsoft, is to get rid of it and buy a computer that can run Windows 11. But that's not good enough. This ThinkPad - like millions of other PCs in the same boat - is still perfectly functional.

Software development

13 hours ago

Google launches Gemma 4 with a broad licensing model

Google DeepMind's Gemma 4 introduces four open-weight AI models for local devices, enhancing developer accessibility and performance.

#open-source

3 hours ago

Software development

Internet Bug Bounty program hits pause on payouts

The Internet Bug Bounty program is pausing submissions for bug reports in open-source software to reassess its approach to security.

How AI has suddenly become much more useful to open-source developers

AI tools are becoming increasingly useful for open-source maintainers, but legal and quality issues remain.

3 hours ago

Software development

Internet Bug Bounty program hits pause on payouts

How AI has suddenly become much more useful to open-source developers

AI tools are becoming increasingly useful for open-source maintainers, but legal and quality issues remain.

Software development

I built two apps with just my voice and a mouse - are IDEs already obsolete?

fromWIRED

Software development

Cursor Launches a New AI Agent Experience to Take on Claude Code and Codex

I built two apps with just my voice and a mouse - are IDEs already obsolete?

AI coding transforms development by replacing traditional editing and debugging with instructive guidance.

fromWIRED

Cursor Launches a New AI Agent Experience to Take on Claude Code and Codex

Cursor 3 enables users to deploy AI coding agents for task completion, marking a shift in developer workflows.

more#ai-coding

Inside KPMG's push to turn tax experts into hands-on software builders

KPMG US empowers tax professionals to build software prototypes alongside engineers, enhancing service delivery and speeding up tool development.

Google's Gemma 4 model goes fully open-source and unlocks powerful local AI - even on phones

Gemma 4 is now fully open-source, enabling local AI use for privacy, offline functionality, and cost savings across various devices.

fromDevOps.com

Why Code Validation is the Next Frontier - DevOps.com

Shared staging environments are inadequate for modern development; isolated, on-demand setups are needed for effective validation.

#ai-development

Software development

OutSystems focuses on control and consistency in AI projects

fromDEV Community

Software development

From Maintaining Open Source Libraries to Building an AI-Powered Tools OS with Rust and WebAssembly

OutSystems focuses on control and consistency in AI projects

OutSystems introduces Agentic Systems Engineering to enhance coherence and control in AI development, addressing fragmentation and integration challenges.

fromDEV Community

From Maintaining Open Source Libraries to Building an AI-Powered Tools OS with Rust and WebAssembly

Kitmul evolved from a modest project to a platform offering over 300 tools, leveraging AI to enhance development speed and user accessibility.

Microsoft rejiggers Intune to give patches time to prove themselves

Microsoft Intune will shift from pushing patches to measuring compliance with defined update standards, emphasizing policy and outcomes over delivery.

Zero-Effort Production Debugging: How I Automated Bug Fixes for My Side Project

Automating bug fixes with an AI agent streamlines maintenance for full-stack applications, enabling zero-effort management of errors.

fromSeangoedecke

Working on products people hate

Working on unpopular products reveals the limited control individual engineers have over product reception.

SystemRescue 13 lands with Linux 6.18 and bcachefs support

SystemRescue 13.0 introduces Linux kernel 6.18, improved HiDPI support, updated bcachefs tools, and GParted Live 1.8.1.

Some 'broken by update' PCs were already doomed

Updates are often blamed for issues that predate them, revealing underlying problems in devices.

Anthropic says its leak-focused DMCA effort unintentionally hit legit GitHub forks

Anthropic's DMCA takedown mistakenly removed legitimate forks of its code, leading to backlash and a request for reinstatement of affected repositories.

22 hours ago

AO3 is finally out of beta after 17 years

Archive of Our Own officially exits beta after 17 years, continuing to improve with ongoing updates and community contributions.

Meta shows structured prompts can make LLMs more reliable for code review

Code review is evolving towards machine-led verification, improving accuracy but introducing tradeoffs like increased latency and workflow overhead.

Vim and GNU Emacs: Claude Code helpfully found zero-day exploits for both

LLMs can quickly identify security vulnerabilities in code, but their rapid evolution poses potential risks.

What next for junior developers?

Software development companies must adapt to the impending retirement of senior developers and the need for wisdom in coding.

Nvidia rolls out its fix for PC gaming's "compiling shaders" wait times

Nvidia's new Auto Shader Compilation feature allows automatic shader compilation during idle times to reduce load times for PC gamers.

#ollama

Software development

Running local models on Macs gets faster with Ollama's MLX support

fromRealpython

How to Use Ollama to Run Large Language Models Locally - Real Python

Ollama allows local running of large language models without API keys or ongoing costs.

Software development

Running local models on Macs gets faster with Ollama's MLX support

fromRealpython

How to Use Ollama to Run Large Language Models Locally - Real Python

Ollama allows local running of large language models without API keys or ongoing costs.

more#ollama

Meet 'Dobby': The AI agent that could kill the app economy

Generative AI and agents threaten the app ecosystem by enabling control of devices through natural language instead of traditional apps.

fromDeveloper Tech News

Google releases Agent Development Kit for Java

Google's Agent Development Kit for Java streamlines AI integration into existing architectures, enhancing multi-language support and reducing integration friction.

The supervisor class: how AI agents are remaking the developer's career | Fortune

The role of software developers is evolving from manual coding to high-level orchestration of AI agents.

fromFast Company

Software development

Manus AI cleaned up my computer-for a price

AI tools like Manus can automate tedious computer tasks, saving time and improving organization.

fromFortune

The supervisor class: how AI agents are remaking the developer's career | Fortune

The role of software developers is evolving from manual coding to high-level orchestration of AI agents.

fromFast Company

Manus AI cleaned up my computer-for a price

AI tools like Manus can automate tedious computer tasks, saving time and improving organization.

The ERP that doesn't care which AI you use, and why that's smart

NetSuite announced three new AI Connector Service extensions, emphasizing a strategic shift towards openness and integration with external AI models.

fromDevOps.com

The Trust Tax Framework: Measuring Developer Confidence in CI/CD Systems - DevOps.com

Test infrastructure credibility is crucial; developers lose trust when re-run rates exceed 30% and override rates surpass 5%.

Memo: Red Hat Global Engineering plans to lean in to AI

Red Hat is pushing AI tooling within its Global Engineering department, evolving roles to prioritize AI automation for customer value delivery.

Discord Open Sources Osprey Safety Rules Engine Processing 2.3 Million Rules per Second

Osprey is an open-sourced event stream decisions engine by Discord, capable of real-time threat detection and mitigation.

fromFortune

Anthropic leaks its own AI coding tool's source code in second major security breach | Fortune

Anthropic leaked the source code for Claude Code, exposing 500,000 lines of code due to a packaging error, raising cybersecurity concerns.

I installed this Arch-based distro my way in under 5 minutes - so can you

The Prism Linux installer makes installing this Arch-based distribution so easy that anyone, regardless of experience, can install Linux. During installation, you can choose which desktop environment you want.

Software development

GitHub removes Copilot messages from pull requests

Developers expressed widespread criticism over Copilot's feature that inserted promotional messages into pull requests, leading to confusion and irritation as these additions resembled advertising.

Software development

Ubuntu beta arrives with GNOME 50, sans Google Drive support

Ubuntu 26.04 beta features GNOME 50, which lacks Google Drive support, impacting users and other distros using this desktop environment.

fromSearch Engine Roundtable

Google On Why Core Updates Take Weeks To Roll Out

Core updates take weeks to roll out due to individual components being pushed step-by-step.

If Microsoft really wants to fix Windows 11, it should do these four things ASAP

Microsoft's focus on Windows 11 fundamentals and reforming the Insider Program is essential for improving user experience.

Windows boss promises to heal the operating system's wounds

Microsoft promises improvements to Windows 11, addressing user frustrations with bugs and AI integration, but lacks genuine apologies for past issues.

Microsoft may finally remove its frustrating Windows 11 setup requirement

Microsoft may allow local accounts in Windows 11, addressing user frustration over mandatory Microsoft account sign-ins.

If Microsoft really wants to fix Windows 11, it should do these four things ASAP

Microsoft's focus on Windows 11 fundamentals and reforming the Insider Program is essential for improving user experience.

Windows boss promises to heal the operating system's wounds

Microsoft promises improvements to Windows 11, addressing user frustrations with bugs and AI integration, but lacks genuine apologies for past issues.

Microsoft may finally remove its frustrating Windows 11 setup requirement

Microsoft may allow local accounts in Windows 11, addressing user frustration over mandatory Microsoft account sign-ins.

A human approach to Agentic AI. One person. One text file. Five agents.

A soft-agent team of AI assists in book creation and management without requiring coding skills.

Okta's CEO on security in the AI era

Okta is adapting to AI challenges by managing both human and AI agent identities for security.

#openai

Software development

OpenAI introduces plugins for Codex and expands functionality

OpenAI Extends the Responses API to Serve as a Foundation for Autonomous Agents

OpenAI extends the Responses API to simplify agentic workflows with new tools and a built-in execution environment.

OpenAI upgrades Codex to automate your workflows - and compete better with Claude Code

OpenAI's Codex introduces plugins to enhance AI workflows and compete with Claude Code, aiming for a broader ecosystem.

Software development

With new plugins feature, OpenAI officially takes Codex beyond coding

OpenAI has introduced plugin support in Codex to enhance user experience and integration with external services.

OpenAI introduces plugins for Codex and expands functionality

OpenAI introduces plugin support in Codex, enhancing integrations and extensibility to compete with rivals like Anthropic and Google.

OpenAI Extends the Responses API to Serve as a Foundation for Autonomous Agents

OpenAI extends the Responses API to simplify agentic workflows with new tools and a built-in execution environment.

OpenAI upgrades Codex to automate your workflows - and compete better with Claude Code

OpenAI's Codex introduces plugins to enhance AI workflows and compete with Claude Code, aiming for a broader ecosystem.

With new plugins feature, OpenAI officially takes Codex beyond coding

OpenAI has introduced plugin support in Codex to enhance user experience and integration with external services.

more#openai

Microsoft pulls Windows update after installation problems

Installation on some devices failed with a 0x80073712 error, and Microsoft temporarily pulled the plug on Friday night. The problem affects Windows 11 24H2 and 25H2.

Software development

fromDanielwestheide

5 days ago

Software development

Pair Programming Considered Unnecessary: The Costs of Productive Solitude

JetBrains is discontinuing Code With Me due to declining demand for remote collaborative coding post-pandemic.

Bluesky's new app is an AI for customizing your feed

Attie is an AI assistant that enables users to create custom feeds and build apps without coding experience.

Microsoft Introduces WinApp CLI to Unify Windows App Development Workflows

WinApp CLI simplifies Windows application development by consolidating tasks into a single command-line tool for various frameworks.

Lucid Introduces Process Agent and Enhances AI Integrations

Lucid Software introduces AI capabilities to enhance diagram creation and documentation, focusing on collaboration and better knowledge management.

fromnews.bitcoin.com

MCP in 2026: 97 Million Downloads and Growing Crypto Infrastructure From Bitgo to Coingecko

Anthropic open-sourced MCP, enabling AI models to connect with external tools and databases, fostering widespread adoption across various platforms.

fromFortune

Cursor CEO warns vibe coding builds 'shaky foundations' and eventually 'things start to crumble' | Fortune

AI is transforming programming by enabling end-to-end tasks, but caution is needed to avoid 'vibe coding' pitfalls.

The Verifier-Compiler Loop: Turning Human Preferences into Production Agent Judgment

Production failures arise from compounded small errors in long workflows, not just isolated prompt failures.

We tried 3 of the biggest vibe-coding platforms. Here's what we thought about how they stack up.

Vibe coding tools allow users to build apps without coding knowledge, but their effectiveness and market sustainability are questioned.

fromThe NodeSource Blog - Node.js Tutorials, Guides, and Updates

2 weeks ago

JavaScript Is Evolving Faster Than Ever - And JSConf Spain Made It Impossible to Ignore

JavaScript is evolving into a platform for intelligence, infrastructure, and decision-making systems, transforming how developers build and think.

Architectural Governance at AI Speed

GenAI accelerates code production, challenging traditional oversight and necessitating a blend of centralized decision-making with automated governance for architectural cohesion.

Inside JPMorgan's push for AI adoption among its sprawling software engineering ranks

JPMorgan Chase mandates software engineers to adopt AI to enhance productivity and coding quality.

fromEntrepreneur

How Software Overload Is Costing You More Than You Know

Software overload occurs when too many tools create complexity, hindering efficiency; the solution is auditing and consolidating tools for simplicity.

fromAnswer.AI

3 weeks ago

So where are all the AI apps? - Answer.AI

Skeptics question the productivity claims of AI tools due to a lack of significant new software creation post-ChatGPT release.

Noi brings all your favorite AI tools together in one desktop interface - no more app switching

Noi simplifies access to multiple AI services through a single user interface.

Visual Studio Code previews chat customizations editor

MCP servers registered in VS Code are bridged to Copilot CLI and Claude agents, allowing user-defined servers and those in mcp.json files to be accessible.

Software development

QCon London 2026: Tools That Enable the Next 1B Developers

AI tooling is transforming web development, leading to a surge in new builders who are not traditional developers.

fromDevOps.com

The AIRE Gap: Why Organizations Are Buying AI SRE Tools They Aren't Ready to Use - DevOps.com

AI reliability engineering promises to enhance incident management, but many organizations are unprepared for its implementation and benefits.

.NET 11 Preview 2 Updates MAUI with Performance Improvements and Platform Refinements

.NET 11 Preview 2 enhances MAUI with updates to Map control, binding performance, and API consistency, focusing on usability and performance improvements.

[Video Podcast] Agentic Systems Without Chaos: Early Operating Models for Autonomous Agents

Agentic systems are evolving to tackle previously unsolvable problems in architecture and engineering.

Wine 11 might be the tipping point that finally pushes gamers from Windows to Linux

Wine 11 enhances Windows game performance on Linux with NTSYNC, eliminating bottlenecks and achieving near-native speeds.

Kali Linux 2026.1 introduces 8 new tools

Kali Linux 2026.1 introduces a theme refresh, eight new tools, and celebrates BackTrack's 20th anniversary with a dedicated mode.

Stop worrying: Instead, imagine software developers' next great pivot

Worrying about worst-case scenarios is unnecessary; choose to imagine positive outcomes instead.

Mozilla dev's "Stack Overflow for agents" targets a key weakness in coding AI

cq aims to enhance coding agents' efficiency by enabling knowledge sharing and addressing outdated information and resource consumption issues.

Stop worrying: Instead, imagine software developers' next great pivot

Worrying about worst-case scenarios is unnecessary; choose to imagine positive outcomes instead.

Mozilla dev's "Stack Overflow for agents" targets a key weakness in coding AI

cq aims to enhance coding agents' efficiency by enabling knowledge sharing and addressing outdated information and resource consumption issues.

more#coding-agents

How Windows 95 fought off badly behaved installers

"This rule relies on the fact that Windows maintains backward compatibility, so the newer version still works even if used by an older program."

Software development

Oracle Fusion Agentic Applications: agents make their own decisions

Oracle's 22 Fusion Agentic Applications operate autonomously, aiming to transition enterprise software to a 'system of outcomes' for various business functions.