Unity launched a first-party Claude Code plugin (Sept 9) that installs 29 engine skills, the Unity CLI, and an MCP server for live Editor control—URP, UI Toolkit, IAP, multiplayer, and more. Claude Code is first; other agents later this year.
Built on Qwen3 14B with 6 base DNA tokens in the same stream as text, it predicts variant effects, regulatory regions and next bases, averaging 66.7% on five DNA benchmarks (self reported, just behind GPT 6.1 Sol at a tiny fraction of the cost) and fitting on one 80 GB GPU or a 15.8 GB Q8 GGUF. It ships a carbon dna skill for coding agents, but it isn't clinically validated, so keep it to research (MarkTechPost breakdown)…
Shown on HN Oct 23, the 11 tool server reads notes (checklists, tables, tags, OCR'd attachment text) as Markdown from a read only database and writes changes character by character through Apple's private NotesShared framework, refusing an edit if the note changed since your agent read it and keeping 20 backups. It needs macOS 26+ on Apple silicon plus Full Disk Access, and it's a brand new one person project, so try it with brew install cask xiaofeng han/tap/apple notes mcp and consider the Read Only tool preset first…
Now GA for Enterprise (Oct 23), every conversation starts as chat and moves into an Anthropic managed cloud VM, network egress off by default, when it needs to run code or touch files, and keeps going after you close the laptop. It's off by default for existing orgs until it switches on Nov 16 (Organization settings Capabilities), and isn't available yet for ZDR, HIPAA ready or CMEK setups (admin guide)…
Forever Security traced a customer's agent trying to install the malicious npm package function color to an AGENTS.md in /Downloads , its working directory, then reproduced the attack on Codex (90% success with a harmless payload) and used a malicious CLAUDE.md to leak Claude Code's OAuth token. There's nothing for vendors to patch, so start agents in the project root, never /Downloads , and read unfamiliar instruction files first…
Out of beta since Oct 22, the gpt 6 luna endpoint for yes/no, pick one and score questions adds prompt caching ($0.01 per 1M cached input tokens, $0.10 uncached, still no output charge), native JSON inputs, images in question instructions, US and EU residency, GPT Live integration, and up to 400 questions per request. Datadog says it scores the risk of agent generated shell commands before running them at 40x faster p95 than frontier models, which makes it a cheap gate for an agent's next step…
Spotted something we missed? Start a thread.
