AI INFRASTRUCTURE

Ray CVE-2025-62593 was exploited by the RondoDox botnet before disclosure, then added to CISA KEV. How to check if your Ray setup is exposed and harden it.

Agent model compression has a hidden tax: quantized and pruned agents lose knowledge first and stay confidently wrong. Why cheaper agents start at the cache.

Cloudflare's Billable Usage API returns usage and cost per product from one FOCUS-aligned endpoint, so agent-created spend is visible without the dashboard.

@cloudflare/computer is an open-source agent runtime: an SQLite-backed shared workspace plus a per-task choice between fast isolates and full Linux containers.

Cloudflare runs Kimi K2.6 and GLM 5.2 on Workers AI with FP8 KV caches, INT4 weights and a KV cache integrity check. What each technique buys on GPU fleets.

Cloudflare Workers can now accept inbound TCP and serve gRPC: a connect() handler via Spectrum, full-duplex gRPC from Containers, and gRPC-web translation.

AI API token relays resell OpenAI, Anthropic, and Google access at up to 97.8% off. How the gray market works and what it means for developers on AI APIs.

Open-weight AI is having its Kubernetes moment, argues Mesosphere co-founder Tobi Knaup. His case, the HN pushback, and what it means for developers.

Qualcomm is acquiring Modular for about $3.9 billion. What the deal means for developers using MAX, Mojo, and hardware-agnostic AI inference beyond CUDA.

Self-host LiteLLM or Kong, or use a managed gateway like Portkey, OpenRouter, or Cloudflare AI Gateway? A factual breakdown of cost, control, and ops tradeoffs.

jamesob's local LLM guide: the $2k and $40k hardware paths, the BIOS and kernel settings that matter, and why multi-GPU setups fail at PCIe and IOMMU.

CBRS stock trended after Cerebras' first public earnings. What public-market scrutiny of fast AI inference means for developers - not investment advice.

Sakana Fugu makes a timely argument for model routing: frontier performance should come from swappable systems, not a hard dependency on one proprietary API.

Factory Router explained: automatic model routing and failover for Droid sessions, which spend and reliability claims are vendor claims, and router vs DIY.

OpenRouter Fusion turns multi-model panels into an API feature. Use it as an escalation lane for prompts where a wrong answer is expensive, not as the default.

Claude Managed Agents added dreaming, outcomes and multi-agent orchestration in 2026. How each primitive works and when to use the three together.

Factory AI's Droid lets you pick a model per task and per subagent. What its routing, BYOK and open-weight tiers reveal about cutting coding agent costs.

LiteLLM vs Portkey vs OpenRouter compared for production AI apps: cost tracking, fallbacks, caching, and load balancing, plus when to use each router.

Cloudflare's Agent Memory primitive. What it stores, how ingest and recall work, how it compares to mem0, and how to wire it into your stack.