80 stories tagged Coding · page 2 of 4
A new research paper reveals that the classical intuition that verifying a solution is easier than producing one is being inverted for today's coding agents. As foundation models get stronger, generating candidate solutions has become easier, while reliable verification—capturing underspecified human intent—has become the harder problem.
OpenAI has unveiled GPT-5.6 Sol, a new AI model that excels in coding, science, and cybersecurity. It also includes advanced safety features to prevent misuse. This could revolutionize how professionals use AI in technical fields.
Dromeas.ai has introduced an AI system that simulates a council of expert programmers to review your code. This could make professional-level code reviews accessible to everyone, not just big tech companies.
Jason Liu shares techniques for using AI to maintain context and manage complex projects over time. This approach can help both developers and non-technical users streamline their workflows.
Transpilatron is an AI tool that converts Python code into C binaries, making it easier to run Python programs on devices with limited resources. This could be a game-changer for developers working with embedded systems or older hardware.
Nextdoor engineers are using OpenAI's Codex with GPT-5.5 to investigate hard-to-reproduce issues, build across platforms, and focus on product outcomes rather than getting stuck on technical hurdles.
Fable 5, a new AI model, has scored as high as GPT-5.5 in a coding performance test. This means everyday users may soon have more affordable options for AI-powered coding help.
Researchers developed CodeAlchemy, a system that generates synthetic code to train AI models. This could make AI coding tools smarter and more versatile for real-world tasks.
Cohere has introduced North Mini Code, a compact AI model designed specifically for developers. The model is open-source, lightweight, and optimized for code generation and completion, making advanced AI capabilities more accessible to a wider audience.
![ReARM: Governing AI Coding Agents Demo [video]](/_next/image?url=%2Fimages%2Farticles%2F2026-06-08-new-ai-system-rearm-demonstrates-how-to-govern-ai-coding-agents.png&w=1200&q=75)
A new system called ReARM demonstrates how to govern AI coding agents, ensuring they follow rules and perform tasks safely. Watch the demo video to see it in action.
Endava is integrating AI agents like ChatGPT Enterprise and Codex into their software development process. This shift is making workflows faster and more efficient, setting a new standard for AI-native enterprises.
A study reveals that AI coding assistants face challenges when they take over tasks from other agents or humans. This 'handoff debt' creates inefficiencies in real-world software development.
A developer secretly added a prompt injection to the jqwik testing tool that tricks AI coding assistants into deleting their own output. This highlights growing tensions between developers and AI tools. The incident raises questions about trust in software development.
Scott Wu, CEO of Cognition, emphasizes that AI coding agents like Devin are meant to assist developers, not replace them. This perspective highlights the importance of human creativity in programming.
A growing number of developers now refuse to work without AI coding assistants, but researchers warn this reliance may lead to lower-quality code and erode essential skills, potentially hurting coders' long-term job prospects.
Braintrust engineers use OpenAI's Codex with GPT-5.5 to quickly turn customer requests into working code. This speeds up development and reduces manual coding time.
Phoenix Code is a new desktop editor where AI can see and interact with your entire page. This could revolutionize how we write and edit code, making it faster and more intuitive.
Warp, a developer tools company, is using OpenAI's GPT-5.5 to create intelligent coding agents that work across local, cloud, and open-source environments. This could make coding faster and more collaborative for everyone.
Researchers have introduced two advanced AI models designed for long-term coding tasks. These models, Laguna M.1 and XS.2, represent a significant leap in AI capabilities for software development.
Cisco is integrating OpenAI's Codex to speed up software development and improve cybersecurity. This partnership aims to automate tasks, reduce errors, and enhance productivity for enterprise teams.
VAEN is a new open-source tool that lets developers package and share AI coding agents as easy-to-use files. It solves the problem of moving complex AI workflows between projects.
Researchers discovered a way for AI models to get better by checking their own work. This could make AI smarter without needing human input, speeding up progress in areas like math, science, and coding.
Harvard researchers have developed an AI system that can automate the coding process for scientific research. This could significantly speed up experiments and make advanced research more accessible to non-experts.
Researchers have developed a way for AI to create computer systems with mathematically proven guarantees of correctness. This could revolutionize fields where mistakes are unacceptable, like aviation or medical devices.