Deleting 19k Lines of Dead Compiler Code Without Trusting the LLM
TheCloudlet demonstrates a method to safely delete 19,000 lines of dead compiler code by using AI to identify candidates and then relying on human verification to avoid errors.
#software
Software
37 stories tagged Software
SWECraft: Simulating AI Teams Working Together in Software Worlds
Researchers from the University of Washington and the Allen Institute for AI introduced SWECraft, a framework that simulates AI agents collaborating on real Python packages in realistic software environments to study scalable multi-agent teamwork.
Behavioral Self-Rewarding (BSR): A New Method Lets AI Agents Self-Evaluate and Improve Software Debugging Without a Separate Reward Model
Researchers introduced Behavioral Self-Rewarding (BSR), a method that lets AI agents judge their own debugging trajectories and improve performance without a separately trained reward model. BSR addresses the limitations of binary rewards in reinforcement learning with verifiable rewards (RLVR) by providing more nuanced feedback on debugging quality.
Cognition Integrates GPT-6 Astra into Devin to Automate Software Testing
Cognition has integrated OpenAI's GPT-6 Astra into Devin, an AI software engineering assistant, to automate code testing and validation. The goal is to reduce the amount of code engineers must manually review, enabling faster and more reliable software releases.
AI Kills 'Security Through Obscurity' as Hackers Reverse-Engineer Proprietary Systems
AI tools are making it easier than ever for hackers to reverse-engineer proprietary software, rendering 'security through obscurity' obsolete. This shift forces companies to focus on stronger, more transparent security measures.
Gartner: $234B in Enterprise Application Software Spend at Risk from Agentic AI
Gartner estimates that $234 billion in enterprise application software spending is at risk of disruption from agentic AI, which can automate complex workflows and reduce the need for traditional software tools.
Spec-Driven Agentic Development (SDAD): How AI Agents Use Detailed Specs to Build Software Autonomously
A new research paper formalizes Spec-Driven Agentic Development (SDAD), a framework where AI agents backed by large language models ingest entire Functional Requirement Documents and repository context to autonomously deliver software, making specification quality the key driver of the AI-native SDLC.
Replit Launches Free Mode with GPT-5.6 Luna for No-Cost Software Creation
Replit has introduced Free Mode, powered by GPT-5.6 Luna, allowing anyone to create software without worrying about token costs. This move democratizes software development by removing financial barriers.
Asana Replaced 5 Years of Engineering Work in 2 Weeks Using OpenAI Codex
Asana used OpenAI's Codex to automate a testing system that would have taken five years to complete manually. The project cost about $12,000 and was finished in just two weeks.
Perplexity’s Personal Computer turns Windows PCs into AI agents
Perplexity has launched its Personal Computer tool for Windows, turning PCs into AI agents that can access local files and apps. This expands access to a powerful AI assistant that was previously only available on Macs.
AINTMA: Six AI Agents That Autonomously Manage Software Testing and Cloud Security
Researchers from ArXiv cs.AI introduced AINTMA, a multi-agent AI architecture that uses six specialized agents to autonomously handle software test discovery, risk assessment, prioritization, execution, generative quality intelligence, and cloud security monitoring. The system aims to transform traditional test management into a self-improving quality intelligence ecosystem for distributed cloud environments.
Most people are paying monthly for software with free open-source alternatives
Many popular paid software tools have free, open-source alternatives available on GitHub. Knowing these options can save you money. Open-source software is developed and maintained by communities, often offering similar features to paid tools.
Why AI Code Reviews Are Still Missing the Mark
A new analysis reveals that AI code review benchmarks often test the wrong things, leading to misleading results. This highlights why AI tools still struggle with real-world coding tasks.
ZML Releases Free Software to Make AI Faster and Cheaper
ZML, a French AI startup backed by Yann LeCun, has released ZML/LLMD, a free tool that speeds up AI inference across many chips. This could lower costs for developers and businesses using AI.
ScarfBench: AI Agents Tackle Enterprise Java Framework Migration
ScarfBench is a new benchmark for testing AI agents on complex Java framework migrations. It helps evaluate how well AI can handle large-scale software updates.
OpenAI's 18-Year-Old Bug Fix: How Core Dump Analysis Saved the Day
OpenAI engineers fixed rare infrastructure crashes by analyzing thousands of core dumps, uncovering both a hardware issue and an 18-year-old software bug. This method could improve the stability of AI systems for all users.
AI Coding Token Costs on Track to Rival Human Developer Payroll
Using AI for coding is becoming as expensive as hiring human developers due to the high cost of token consumption for complex projects. This trend is prompting companies to rethink how they budget for software development, as massive model usage can rival the cost of a full-time developer.
OpenAI Launches New Initiative to Help Find and Patch Open Source Bugs
OpenAI has launched a new initiative to help find and patch bugs in open-source software, using AI to scan code for vulnerabilities and suggest fixes. This could make widely used tools more secure for everyone.
New Language Defines AI's Role in Software Development
Researchers propose a new language to clearly define how AI and humans should work together in software development. This could make teamwork between people and AI more predictable and reliable.
OpenAI Launches 'Patch the Planet' to Support Open-Source Maintainers
OpenAI's new initiative, Patch the Planet, uses AI and expert review to help open-source maintainers find and fix vulnerabilities. This could make open-source software safer for everyone.
Elastic Agrees to Acquire AI-Powered Bug Detection Startup Deductive AI for Up to $85M
Elastic, known for search and analytics, is buying Deductive AI, a three-year-old startup backed by CRV that uses AI to find and fix software bugs. The deal is worth up to $85 million, highlighting the growing importance of AI in software development.
YeasierAgent: A New Way to Build AI-Powered Apps Together
Researchers introduced YeasierAgent, a system that lets users and AI agents collaborate to build apps. It rethinks how software is created, making it more flexible and social.
Dozens of Red Hat packages compromised via official NPM channel
Red Hat has confirmed that multiple packages in its official NPM channel were backdoored, and anyone who has downloaded the affected packages should investigate immediately. The attack is a supply chain compromise through the company's own official npm channel.
AI Coding Agents Struggle With Interruptions, New Research Finds
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.