#Software Development
50 articles with this tag
Reviewing AI's Code Contributions
AI-generated code is flooding pull requests. Learn how to spot the hidden technical debt and subtle bugs these agents introduce.
Missions: AI Agents That Ship for Days
Luke Alvoeiro from Factory discusses how multi-agent systems, like their 'Missions' platform, can overcome human attention bottlenecks in software engineering.
Cielara Code Outperforms Rivals
Cielara Code, from Causal Dynamics Lab, significantly improves AI coding agent performance by mapping production software, outperforming rivals in key benchmarks.
MCP Apps: Building the Future of AI Interactions
Liad Yosef and Ido Salomon of MCP Apps discuss their standard for building interactive UI components within AI chat interfaces, enabling seamless application experiences across platforms.
Anthropic's Boris Cherny: Coding is Solved, What's Next?
Boris Cherny of Anthropic argues that AI has 'solved' coding, shifting the focus to higher-level problem-solving and AI interaction for developers.
Build Dumb AI Loops That Ship with Chris Parsons
Chris Parsons of Cherrypick discusses how to build effective AI loops and products by focusing on simplicity and iteration.
AI Agents: CLI vs. MCP for Tool Selection
IBM's Martin Keen explains how AI agents use CLI commands or the more descriptive Model Context Protocol (MCP) to select and utilize tools, highlighting the benefits of structured data for AI.
AI Engineers: Context is the New Code
Patrick Debois outlines the 'Context Development Lifecycle' for AI agents, emphasizing that 'context is the new code' and detailing the process from generation to observation.
Max Schoening: AI's Role in Design and Product
Notion's Head of Product, Max Schoening, discusses how AI is transforming design and product development, emphasizing agency and the augmentation of human creativity.
Cursor's Agent Harness Gets Smarter
Cursor is meticulously refining its AI agent harness, focusing on dynamic context, rigorous evaluation, and model-specific customization to boost software development capabilities.
GitHub Battles Outages Amid AI Boom
GitHub faces massive infrastructure challenges due to the rapid adoption of AI-powered agentic development workflows, leading to recent outages and a push for 30X scalability.
Applied Intuition: AI for Safer Autonomous Systems
Peter Ludwig of Applied Intuition discusses how their platform accelerates the development of safer AI for autonomous vehicles and other physical systems.
AgentCraft: Gaming the AI Agent Workflow
Ido Salomon unveils AgentCraft, a platform that visualizes AI agent workflows using game-like interfaces, fostering human-AI collaboration and task management.
Replit's Agent 4: AI Building Apps Without Code
Replit CEO Amjad Massad introduces Agent 4, an AI app builder that transforms ideas into functional software with natural language prompts.
OpenAI's GPT-5.5: A Leap in AI Coding Assistance
OpenAI's Romain Huet and Ramp's Will Koh discuss GPT-5.5's advanced coding assistance and its impact on financial data extraction.
AI Needs Fundamentals: Matt Pocock on Code Quality
Matt Pocock emphasizes that AI in coding requires solid software fundamentals, clear design concepts, and a shared language to avoid common pitfalls and produce quality code.
Garry Tan on Building with AI Agents
Garry Tan, CEO of Y Combinator, discusses the emerging era of AI agents in software development, showcasing his G stack tool and the 'conductor pattern' for efficient, AI-assisted development.
NAB Picks Cursor AI Over Rivals
National Australia Bank standardized 6,000 developers on Cursor AI, achieving 3x faster legacy modernization and rapidly developing new applications.
Cursor Taps SpaceX for AI Training Boost
Cursor partners with SpaceX to access xAI's Colossus infrastructure, aiming to overcome compute limitations and enhance its AI model training.
OpenAI Launches Codex Labs for Enterprise
OpenAI launches Codex Labs and partners with GSIs to drive enterprise adoption of its AI coding assistant, expanding beyond development tasks.
AI Agents: The Next Application Layer?
Vercel CTO Malte Ubl discusses the rise of AI agents as the next application layer, exploring their impact on software development, infrastructure, and the future of AI innovation.
Cloudflare's AI Code Review Overhaul
Cloudflare has engineered a sophisticated, multi-agent AI code review system to eliminate bottlenecks and improve code quality.
AI's Impact on Software Development: A New Era
Balaji Srinivasan discusses how AI is transforming software development, making it faster, cheaper, and more adaptive.
AI Code Generation: The Unseen Complexity
The rise of AI in code generation is transforming software development, but it brings challenges in understanding and verifying AI-generated code.
Databricks Tames Coding AI Chaos
Databricks introduces Unity AI Gateway to manage AI coding agents, offering centralized governance, cost controls, and observability for enterprises.
AI Agents: From "Slop" to "Sufficiently Detailed Specs"
Mario Zechner critiques the current state of AI coding agents, highlighting limitations and advocating for a more focused, extensible, and human-guided approach to development.
OpenAI's Codex: Bridging AI and Code Development
OpenAI's Codex is expanding its capabilities, now integrating with Xcode for debugging, generating images, and connecting to numerous developer tools for comprehensive workflow management.
OpenAI Codex Gets Smarter, Broader
OpenAI's Codex AI receives a major update, enabling it to operate computer applications, generate images, and remember user preferences, enhancing developer workflows.
GPT-5.2 Boosts Dev Work, Shifts Focus
New research shows GPT-5.2 and similar AI models are boosting developer productivity, shifting tasks towards complexity and management.
Braintrust CEO: Codex Speeds Up Feature Iteration
Braintrust CEO Ankur Goyal explains how their tool, Codex, enables real-time feature iteration and feedback, bypassing traditional development backlogs.
AI Agents and the Future of Software Development
Ted Mortonson, Managing Director of Technology at Baird, discusses how AI agents are causing a structural shift in software development and the broader economy.
Bugbot Learns From Live Code Reviews
Cursor's Bugbot AI code reviewer achieves nearly 80% bug resolution by learning from live developer feedback and generating custom rules.
GitHub Universe 2026: Call for Speakers
GitHub Universe 2026 is calling for speakers. Submit your proposals by May 1st for the October 28-29 event in San Francisco.
GitButler Raises $22M Series A
GitButler is rebuilding version control for AI-driven development, raising a $22M Series A led by a16z.
AI Engineering: Building Better Platforms
Juan Herreros Elordoy of Banking Circle discusses how to build effective platforms for AI agents, emphasizing self-service, API-based design, and clear documentation.
Baz's Nimrod Hauser on Bending MCP Servers
Baz's Nimrod Hauser discusses best practices for integrating third-party tools into AI agents, focusing on curation, wrapping, guardrails, and tool composition.
AI in Code: Risk & Reward with Patrick Nyeste
Patrick Nyeste of IBM discusses how AI is changing software development, emphasizing the need for shift-left security and real-time risk intelligence.
Copilot CLI adds a 'Rubber Duck' reviewer
GitHub Copilot CLI's new 'Rubber Duck' feature uses a second AI model to review code plans, aiming to catch errors and improve performance on complex tasks.
GitHub's Diff Performance Overhaul
GitHub overhauls its pull request interface, dramatically boosting performance for large code changes through targeted optimizations and simplified architecture.
Claude Code Leak: What Developers Can Learn
Anthropic's Claude Code source code was leaked via an npm registry source map, revealing key features like per-turn instruction loading and efficient subagent parallelism.
Agentic Dev Reshapes Databases
Agentic software development is transforming databases, demanding agility, cost-efficiency, and open ecosystems from infrastructure.
AI is Changing Software Development Lifecycles
Goldman Sachs CIO Marco Argenti and other experts discuss how AI is transforming software development, shifting from experimentation to integrated workflows.
GitHub Copilot to Use User Code for Training
GitHub Copilot will now use user code for AI training, with an opt-out option for Free and Pro users starting April 24.
AI Coding Benchmark Scores Skewed by Infrastructure
Infrastructure configuration, not just AI model prowess, can significantly skew benchmark results, complicating deployment decisions.
Exa Unveils New Code Search Benchmarks
Exa.ai releases 'WebCode', a new benchmark suite for evaluating search performance in coding agents, addressing limitations in existing tools.
Databricks' coSTAR for AI Agents
Databricks details its coSTAR methodology for rapidly and safely deploying AI agents, addressing key testing challenges.
AI Overwhelms Open Source Mentorship
AI-generated code is overwhelming open source maintainers, forcing a rethink of mentorship strategies to focus on comprehension, context, and continuity.
Cursor Agents Expand Beyond Engineering
Money Forward deploys Cursor's AI coding agents across engineering, product, design, and QA, boosting efficiency and saving developers significant time.
Cursor Automates Security with AI Agents
Cursor leverages autonomous security agents to automate vulnerability detection and repair, significantly boosting PR velocity and securing its codebase.
Codex Security Ditches SAST Reports
OpenAI's Codex Security agent bypasses SAST reports, focusing on code behavior and intent to find deeper vulnerabilities.