Follow the latest coverage, related explainers and connected technology stories.
Anthropic announced the Opus 5.5 model, while OpenAI unveiled GPT-6 Sol and GPT-6 Luna, with a shared focus on reducing usage costs and improving coding and adherence to safety controls. The results of the comparisons and proposals for external evaluation standards still require independent verification.
JetBrains proposes evaluating coding agents beyond task-resolution rates by analyzing efficiency, patch quality, and execution paths. A comparison of Claude Opus 4.7 and Gemini 3.5 Flash shows that similar final results can conceal major differences in cost, verification, modification scope, and approaches to handling software repositories.
The results of JetBrains’ global 2026 survey reveal that coding agents write around 47% of the code produced by professional developers, according to participants’ estimates, but fully relying on them remains a minority practice. Clear differences appear based on experience, AI tool, programming language, and geographical region.
The article discusses how developers’ trust in tools is shaped by familiarity and clear processes, and why AI agentic coding tools reveal weaknesses in the software development life cycle instead of automatically solving them. It concludes that building trust requires human responsibility and processes that can be shared and improved, not merely new tools.