Devlery

Devlery - AI news for builders

DEVLERYDEVLERYDEVLERY

Devlery blog

AI news for builders.

Claude Gets a Conscience Tool, and Alignment Moves Into the Agent Loop

Claude Gets a Conscience Tool, and Alignment Moves Into the Agent Loop

Anthropic is widening the moral formation conversation around Claude while testing an ethical reminder tool inside the model runtime loop.

Review comments become run buttons in Copilot Agent Merge

Review comments become run buttons in Copilot Agent Merge

GitHub Copilot app, low-cost model routing, Fix batch, and Agent Merge are turning PR review into an agent execution loop.

Goal Mode by default, Codex targets agent waiting time

Goal Mode by default, Codex targets agent waiting time

OpenAI Codex Goal Mode and locked computer use move the coding-agent bottleneck from prompts toward goals, context, approvals, and policy.

84 Malicious Versions, and the Supply Chain Mine Under AI Development

84 Malicious Versions, and the Supply Chain Mine Under AI Development

The TanStack npm attack reached OpenAI employee devices and app signing certificates, exposing the supply chain boundary around AI development environments.

Agents Need PCs Too, and Windows 365 Defines the Isolation Layer

Agents Need PCs Too, and Windows 365 Defines the Isolation Layer

Windows 365 for Agents isolates AI agent execution inside Cloud PCs and pairs with Agent 365 governance.

Antigravity 2.0, Google Turns the IDE Into an Agent Command Center

Antigravity 2.0, Google Turns the IDE Into an Agent Command Center

Google Antigravity 2.0 connects the IDE, CLI, SDK, Gemini API managed agents, and Android app generation into one agent operating surface.

Agents compiled into ABL, and the runtime bottleneck Kore.ai is targeting

Agents compiled into ABL, and the runtime bottleneck Kore.ai is targeting

Kore.ai Artemis frames enterprise agents as compiled ABL artifacts controlled by runtime governance, not loose prompt bundles.

OpenAI’s unit-distance proof puts AI research automation on the record

OpenAI’s unit-distance proof puts AI research automation on the record

OpenAI’s counterexample to the Erdős unit-distance conjecture shows both the promise of AI research automation and the reproducibility gap left by an unnamed model.

SKILL.md is not documentation, it is the new signed supply chain

SKILL.md is not documentation, it is the new signed supply chain

NVIDIA Verified Agent Skills treats agent skills as scanned, carded, and signed artifacts, pointing to a new supply-chain checkpoint for AI agents.

SageMaker opens an OpenAI-compatible door for enterprise LLM infrastructure

SageMaker opens an OpenAI-compatible door for enterprise LLM infrastructure

AWS SageMaker AI now supports OpenAI-compatible inference endpoints, moving enterprise LLM friction from model deployment toward API surfaces, IAM, and routing layers.

The 160ms Action Channel Voice Agents Need

The 160ms Action Channel Voice Agents Need

The DuplexSLA paper reframes real-time voice-agent latency around a 160ms action channel where speech, planning, and tool calls share one timeline.

88-Core Vera Shows Agent Bottlenecks Moving To The CPU

88-Core Vera Shows Agent Bottlenecks Moving To The CPU

NVIDIA Vera CPU deliveries show that AI agent competition is shifting beyond GPU inference toward CPU-bound sandboxes, tool calls, and RL evaluation.