A developer created a 40-line Python tool, blast_radius.py, that scores an AI agent's API key blast radius from 0 to 100 based on permission metadata, without reading the secret value or contacting an…
Logs have traditionally been ignored until system failures, but the rise of autonomous AI agents introduces new challenges for observability that traditional logging cannot address.…
The US government's June 12 order barring foreign nationals from accessing Anthropic's Claude Fable 5 and Mythos 5 models led to a global takedown of both models, exposing a compliance gap in frontier…
The AI coding discourse has shifted from debating whether agents can write production code to focusing on verification challenges as loops replace prompts. The New Stack reports that verification is b…
AI practitioners are prioritizing model triage to cut costs, as running the same coding task through Claude Fable 5 costs $9 versus $1.50 for GPT-5.5, a 6x gap. Three signals reinforce cost pressure: …
The enterprise agent wars are intensifying as companies vie to become the neutral platform, akin to Switzerland, in the AI agent ecosystem. The New Stack explores which players might assume this role …
AI is eliminating many entry-level tech roles traditionally filled by junior developers, system administrators, and IT support staff, as companies increasingly automate coding, testing, and infrastruc…
AI agents writing directly to production databases are forcing a shift away from manual data management models, according to industry experts. The rise of agentic AI systems that autonomously read and…
AI's complexity has rendered traditional debugging methods like stack traces insufficient for modern software development. The industry now requires a new debugging paradigm that accounts for machine …
Cloud-native software development increasingly relies on asynchronous AI agents, but their utility depends entirely on the ability to verify the outputs they produce. Verification for these agents is …
A new approach enables developers to transform AI coding agents into deterministic Java Spring experts, offering precise and reliable code generation for enterprise applications. The method focuses on…
Sonar has launched SonarSweep, a tool designed to clean AI training data and reduce software bugs by removing low-quality or erroneous code from datasets used to train large language models. The tool …
Ramp is deploying forward-deployed engineers to build custom finance AI solutions, betting that tailored, in-house development can outperform off-the-shelf AI tools for enterprise expense management. …
A 23-year-old software vulnerability known as Spring has been reclassified as a security emergency due to new AI-driven exploitation techniques. The flaw now poses an immediate and critical threat to …
Lindy, an AI agent startup, switched its underlying model from Anthropic to DeepSeek and reports saving millions of dollars in inference costs. The company made the change to address the rising expens…
Software engineering leaders are competing to build the most "joyous" products as a new "agent war" begins in the industry. The outcome of this competition will determine which companies win user adop…
The New Stack reports that transitioning AI systems from Jupyter Notebook experimentation to production demands fundamental shifts in mindset, architecture, and engineering discipline, with no relianc…
A user's RAG-powered customer-support agent incorrectly approved a laptop return because it retrieved a 2023 return policy document instead of the current 14-day policy, despite the query being semant…
Agentic AI is driving enterprises to prioritize operations platforms as the most critical infrastructure layer, surpassing models and data science talent in importance. The shift to hybrid environment…
The New Stack published a guide detailing how Azure Kubernetes Service (AKS) can secure AI agent workloads on shared GPU clusters using four control layers: networking, policy enforcement, container i…