Agents & Frameworks

Neural Computers' Symbolic Stability Failure Contradicts the Case for Pure-Neural Agent Orchestration

Meta AI and KAUST's Neural Computers paper names routine reuse, controlled updates, and symbolic stability as open problems — exactly what LangGraph and AutoGen already solve.

Models & Research

Self-Correction Comes to Diffusion Models: What SOAR Means for Iterative Image Generation Pipelines

Tencent's SOAR replaces SFT post-training in diffusion models, yielding an 11% GenEval lift on SD3.5-M — no reward model, no preference labels required.

· 6 min read
Culture & Society

EU's 2027 Replaceable Battery Mandate: What It Means for Phone Buyers and Repairers Right Now

The EU's 2027 battery mandate is confirmed. Here's what 'user-replaceable' legally means, which phones comply now, and how to buy smart before the rules change.

· 6 min read
Security

TeamPCP Backdoored LiteLLM via a Poisoned CI Scanner: What It Means for Every AI Python Stack

TeamPCP stole LiteLLM's PyPI token through a compromised Trivy GitHub Action, shipping credential-stealing releases to 36% of monitored cloud environments.

· 7 min read
Infrastructure & Runtime

KV Cache Is Becoming a Distributed Infrastructure Layer: What KV Packet and llm-d Mean for Self-Hosted LLM Teams

KV Packet eliminates cross-request recomputation; llm-d brings cache-aware routing to Kubernetes. Here's what both mean for vLLM capacity planning.

· 6 min read
Ethics, Policy & Safety

Symbolic Guardrails for AI Agents: Hard Safety Guarantees Without Crippling Capability

A new paper shows symbolic guardrails can push agent safety to 100% in regulated domains without capability loss — but only for 74% of real-world policies.

· 6 min read
Developer Tools

ACP Registry Is Live: Zed and JetBrains Just Did for AI Agents What LSP Did for Language Servers

The ACP Agent Registry lets developers install AI coding agents once across JetBrains and Zed. Here's what the migration path looks like and whether to commit.

· 6 min read
Ethics, Policy & Safety

America's AI Researcher Pipeline Dropped 89%. What the Stanford Index Means for Teams Hiring AI Engineers

Stanford's 2026 AI Index reports an 89% collapse in AI researcher inflows to the US. Here's what it means for teams actively building AI engineering capacity.

· 6 min read
Ethics, Policy & Safety

Atlassian Turned On AI Training Data Collection by Default — Here's What to Disable

Atlassian's data contribution policy sends Jira and Confluence content to AI training by default. Here's the exact settings path to opt out before August 17.

· 6 min read
Developer Tools

Cloudflare Browser Run's CDP and MCP Support: Serverless Browser Automation for AI Agents

Cloudflare renamed Browser Rendering to Browser Run in April 2026 and added CDP and MCP support, letting AI agents use managed headless Chrome with a single config change.

· 6 min read
Open Source

Devstral 2 from Mistral: A Fully Open-Source Coding Agent Model You Can Run on a Laptop

Devstral Small 2 is genuine Apache 2.0 and fits in 14 GB. The 123B flagship looks open-source but carries a revenue cap most enterprises will violate.

· 6 min read
Open Source

ggsql Alpha: Write ggplot2-Style Visualizations Directly in SQL

Posit shipped the ggsql alpha today — a SQL extension that adds grammar-of-graphics clauses to DuckDB and SQLite queries. Here's what works, what's missing, and when to use it.

· 6 min read
Open Source

GitHub CLI's `gh skill` Command: One Standard to Rule [Claude Code](/articles/free-claude-code-routes-claude-code-through-nvidia-nim-and-local-models-after/), Copilot, Cursor, and Gemini

GitHub shipped `gh skill` in public preview on April 16, 2026. Here's how the command works, what the open Agent Skills spec promises, and why the ecosystem is already compromised.

· 6 min read
Infrastructure & Runtime

Google Cloud Is Doubling Peering Egress Costs on May 1. Here's What to Audit Before Then

GCP doubles North America CDN Interconnect and Direct Peering rates May 1. Here's how to find your exposure in 10 minutes and rank your mitigation options.

· 6 min read
Security

Jailbreak Scaling Laws: Why Reasoning Models Are Now the Cheapest Attack Vector Against Other LLMs

Two converging studies show LRMs achieve 97% autonomous jailbreak success and exponential scaling — here's what that means for production deployments.

· 6 min read