Privacy laws target AI, smart glasses right to erase Australians’ data

Anthropic's Model Hardware Standard: AI Agents Are Expanding From Software Tools to Physical Systems

Anthropic opened a research preview of the Model Hardware Standard (MHS) on August 28, 2026 , describing it as a shared specification that allows AI agents to safely operate programmable physical…

• Anthropic released Model Hardware Standard (MHS) preview on August 28, 2026.
• MHS standardizes interface for AI agents to manage physical devices in research and manufacturing.
• Transition enables agents to interact directly with hardware through common commands.

1h ago ·dev.to

Stop Letting Flaky APIs Crash Your AI Agents

How to combine exponential backoff, circuit breakers, and graceful fallbacks for production-grade agentic workflows. The Bottleneck in Production AI agents are only as reliable as the tools they…

1h ago ·dev.to

OpenAI Jalapeño puts NVIDIA's inference margins on the clock

Does Jalapeño beat NVIDIA? On the benchmark OpenAI published, yes. Does that make it a better chip than NVIDIA's Blackwell platform? The evidence does not support that claim yet. Should NVIDIA care?

• OpenAI unveiled its first custom ASIC, Jalapeño, for LLM inference.
• Jalapeño aims to reduce inference costs and improve performance per watt.
• Deployment in racks planned for second half of 2026, with program through 2029.

1h ago ·dev.to

Live API specs for coding agents

Live API specs for coding agents An agent writing frontend code has to know the backend's API. It has three options. It can read the backend source and work out from scratch what the service already…

• docs-mcpserver simplifies coding frontend agent apps with live API specs.
• Agent accesses backend API via cached OpenAPI document, definition name, or keyword search.
• Advantages include reduced code burden, always-up-to-date specs, and uninterrupted development.

1h ago ·dev.to

Build a Tested Agent Skill with SKILL.md and Python Scripts

AI agents are good at interpreting goals, but prose instructions are a weak place to enforce exact rules. If a skill says "keep the commit subject short" or "never commit without approval," an agent…

• SKILL.md file defines agent skill's contract and validation boundaries
• Python validator enforces Conventional Commit message rules
• Repository includes unit tests for validator's accuracy

1h ago ·dev.to

Claude Session URL appended to commit messages and PR descriptions by default

1h ago ·github.com