IBM says the biggest challenge in AI-powered software development is no longer generating code. Instead, the company argues that reviewing and validating AI-generated code has become the real bottleneck, prompting new multi-agent capabilities and modernization tools for its Bob platform.
SpaceXAI has launched Grok 4.5, its newest flagship AI model, claiming it outperforms GPT 5.5 on coding benchmarks while delivering faster, more efficient performance.
A new GitLab survey suggests AI coding tools are boosting productivity, but many organizations are struggling to track, govern, and maintain the code those tools generate.
Block has unveiled Builderbot, an internal AI platform that the company says is already responsible for roughly 15 percent of its production code changes. The system can write code, open pull requests, monitor CI pipelines, and work across Block’s massive codebase, highlighting how AI is becoming an increasingly important part of modern software development.
Cloudflare has acquired VoidZero, the company behind Vite and several major JavaScript development tools. The company promises everything will remain open source and vendor neutral, but developers may still have concerns about growing consolidation in the AI-native web stack.
Virgin Atlantic says OpenAI Codex helped developers shrink legacy codebases, improve testing coverage, and dramatically speed up software development during high-pressure airline deployments.
OpenAI is bringing Codex to the ChatGPT mobile app, allowing developers to monitor AI coding agents, approve commands, and manage remote development environments from anywhere.
Building apps with AI is easy now. Running them is not. Hosting.com thinks it has a solution, but does it really fix the problem?
GitLab is pushing agentic AI deeper into development workflows with version 18.10, but developers may question whether they actually need it.
OpenAI wants Astral’s tools to turn Codex into something bigger than a code generator, and that could reshape how Python developers work.
Chrome will ship stable releases every two weeks starting in September 2026. With AI accelerating software development, some may wonder why not weekly or even daily updates.
OpenAI has launched GPT-5-Codex, a version of GPT-5 designed for real-world coding. It reviews code, fixes bugs, and works across terminals, IDEs, GitHub, and mobile.