News

infoq.com
infoq.com > news > 2026 > 01 > claude-code-creator-workflow

Inside the Development Workflow of Claude Code's Creator

13+ hour, 1+ min ago   (738+ words) Live Webinar and Q&A: A Reference Architecture for Building Trustworthy Agentic AI Systems (Jan 22, 2026) Save Your Seat Somtochi Onyekwere explains the architecture of Corrosion, a distributed system designed for low-latency state replication. She shares how Fly.io transitioned from Consul…...

infoq.com
infoq.com > articles > agentic-terminal-cli-agents

Agentic Terminal - How Your Terminal Comes Alive with CLI Agents

3+ day, 1+ hour ago   (1591+ words) Live Webinar and Q&A: A Reference Architecture for Building Trustworthy Agentic AI Systems (Jan 22, 2026) Save Your Seat In this end-of-year panel, the InfoQ podcast hosts reflect on AI's impact on software delivery, the growing importance of sociotechnical systems, evolving cloud…...

infoq.com
infoq.com > news > 2026 > 01 > intel-deepmath-llm-architecture

Intel DeepMath Introduces a Smart Architecture to Make LLMs Better at Math

5+ day, 13+ hour ago   (464+ words) Sub100-ms APIs emerge from disciplined architecture using latency budgets, minimized hops, async fanout, layered caching, circuit breakers, and strong observability. But longterm speed depends on culture, with teams owning p99, monitoring drift, managing thread pools, and treating performance as a shared,…...

infoq.com
infoq.com > news > 2026 > 01 > duckdb-iceberg-browser-s3

DuckDB's WebAssembly Client Allows Querying Iceberg Datasets in the Browser

6+ day, 21+ hour ago   (720+ words) Naveen Mareddy and Sujana Sooreddy discuss the evolution of Netflix's media processing observability, moving from monolithic tracing to a high-cardinality analytics platform. They explain how to handle "trace explosion" using stream processing and a "request-first" tree visualization, and share how…...

infoq.com
infoq.com > news > 2026 > 01 > microsoft-llm-contextual-privacy

Microsoft Research Develops Novel Approaches to Enforce Privacy in AI Models

1+ week, 1+ day ago   (631+ words) Naveen Mareddy and Sujana Sooreddy discuss the evolution of Netflix's media processing observability, moving from monolithic tracing to a high-cardinality analytics platform. They explain how to handle "trace explosion" using stream processing and a "request-first" tree visualization, and share how…...

infoq.com
infoq.com > news > 2025 > 12 > aws-well-architected-drhc-lens

AWS Expands Well‑Architected Guidance with Data Residency and Hybrid Cloud Lens

1+ week, 5+ day ago   (332+ words) As AI evolves from tool to collaborator, architects must shift from manual design to meta-design. This article introduces the "Three Loops" framework (In, On, Out) to help navigate this transition. It explores how to balance oversight with delegation, mitigate risks…...

infoq.com
infoq.com > news > 2025 > 12 > qconai-architecural-amnesia

QCon AI NY 2025 - Becoming AI-Native Without Losing Our Minds To Architectural Amnesia

2+ week, 2+ day ago   (536+ words) As AI evolves from tool to collaborator, architects must shift from manual design to meta-design. This article introduces the "Three Loops" framework (In, On, Out) to help navigate this transition. It explores how to balance oversight with delegation, mitigate risks…...

infoq.com
infoq.com > news > 2025 > 12 > cactus-on-device-inference

Cactus v1: Cross-Platform LLM Inference on Mobile with Zero Latency and Full Privacy

2+ week, 3+ day ago   (549+ words) As AI evolves from tool to collaborator, architects must shift from manual design to meta-design. This article introduces the "Three Loops" framework (In, On, Out) to help navigate this transition. It explores how to balance oversight with delegation, mitigate risks…...

infoq.com
infoq.com > presentations > llm-ai-africa

Ecologies and Economics of Language AI in Practice

2+ week, 3+ day ago   (358+ words) As AI evolves from tool to collaborator, architects must shift from manual design to meta-design. This article introduces the "Three Loops" framework (In, On, Out) to help navigate this transition. It explores how to balance oversight with delegation, mitigate risks…...

InfoQ
infoq.com > news > 2025 > 12 > ax-hyperparameter-optimization

Meta's Optimization Platform Ax 1.0 Streamlines LLM and System Optimization

Meta's Optimization Platform Ax 1.0 Streamlines LLM and System Optimization3+ week, 4+ day ago   (507+ words) Francisco Javier Arceo explored Feast, the open-source feature store designed to address common data challenges in the AI/ML lifecycle, such as feature redundancy, and low-latency serving at scale. Peter Hunter & Elena Stojmilova share Open GI's journey from a slow,…...