A software team lead argues that classic pull-request code review breaks down when AI agents generate most of the code, and describes replacing it with a "pair planning and pair validation" model in w…
A blog post argues that traditional prose runbooks are an architectural dead end in the AI era because AI agents cannot read Grafana screenshots, SSH into bastion hosts, or run scripts from personal h…
Nvidia Developer Relations Manager Igor Dmochowski said at Infobip Shift 2026 that the compute required to process an LLM's context grows quadratically with context length, making it unscalable for pr…
Only 7% of organizations running AI workloads on Kubernetes deploy them daily, while 66% already deploy AI on Kubernetes and 47% do so occasionally, according to figures Apple Principal Engineer and C…
Figma Designer Advocate Hugo Raymond warned at Infobip Shift 2026 that AI-generated prototypes can hide unresolved decisions by filling in gaps before teams make them, making a polished prototype look…
Google DeepMind's VP of Technology said AI's next major step is recursive self-improvement, in which systems generate their own experience and data rather than relying on human-generated training data…
OpenAI forward deployed engineer Luis Velasco said the emerging field of "meta software engineering" requires engineers to build systems around AI agents rather than write predefined software sequence…
A new engineering essay argues that teams should move operational workflows into Slack by building thin bots that route commands to internal tools, rather than relying on ad hoc AI conversations for t…
A developer who switched from backend and database architecture to native iOS development credits AI tools, specifically Claude Code, for helping them adapt quickly to the new role. The developer, who…
Benoit Schillings, VP of Research at Google DeepMind, said the mundane work of writing code is going away as AI takes over generation, shifting engineers' focus to problem definition, validation, secu…
A developer's red-teaming exercise demonstrates that AI agents remain vulnerable to prompt injection attacks, using a spreadsheet-based task to show how hidden instructions in Excel files can manipula…
AI tools are making junior developers faster at writing code, but experienced engineers warn that over-reliance can weaken foundational learning and produce overengineered solutions. In interviews, Fr…
Model Context Protocol (MCP) servers can inject thousands of tokens into an AI agent's context window with every request, as a real example showed 2 MCP servers adding 13,000 tokens, roughly 9,750 wor…
At the WeAreDevelopers World Congress 2026 in Berlin, Apryse Solutions Engineer Luca Mancinelli said that AI systems are only as good as the document pipeline behind them, emphasizing that poor PDF pa…
At the RAISE Summit in Paris, Cursor COO Jordan Topoleski and Nokia CTO Pallavi Mahajan discussed how AI adoption in software teams has evolved through three stages, with the third stage requiring com…
At the Raise Summit in Paris, Richard Kirby, Office of the CTO at 1Password, discussed the company's shift toward passkeys and AI credential management, noting that passwords remain prevalent but the …
Netlify's CTO Dana Lawson said that developers learn more from shipping 30 imperfect apps than from one perfect tutorial, citing the company's Hot App Summer challenge where participants built one AI-…
At the AI Engineer World Fair, AWS Developer Advocate Mike Chambers said production AI failures usually stem from the 'harness'—the infrastructure and deployment setup—rather than the model itself, an…
A senior engineering leader argues that AI coding tools like Claude Code can boost code-generation throughput by up to 10x, but human engineers remain the bottleneck because the surrounding engineerin…
At the WeAreDevelopers Conference in Berlin, Aerospike Principal Solutions Architect Zohar Elkayam said engineering teams make a costly mistake by choosing databases based on familiarity rather than w…