ifai.io · Sat 14 Nov

Saturday 14 November

Claude Code gets mods: hack its UI and tools with TypeScript · IFAI

Claude Code gets mods: hack its UI and tools with TypeScript

AI-generated summary Anthropic rolled out mods for Claude Code to let developers customize the interface and agent logic using TypeScript functions. Anthropic states that these mods run with full machine access, which creates security risks when installing untrusted third-party code.

Earlier:

Researchers allege DeepSeek, Kimi, and other Chinese AI models were trained using banned Nvidia Blackwell GPUs — Researchers use new GPU 'fingerprinting' technique to identify the GPUs used to train open models

AI-generated summary Researchers at UnemploymentLabs allege that Nvidia Blackwell chips were used to train Chinese artificial intelligence models including DeepSeek V4 and Kimi K3.1. The researchers applied a fingerprinting technique analyzing weight initialization patterns to identify the hardware families used for training open-weight models.

Also covered byThe RegisterTopFiveIFAI
Earlier:

Anthropic Explains Five Building Blocks of Always-On AI Agents

AI-generated summary Anthropic published a guide titled Building always-on agents that outlines how to create AI assistants that remain available around the clock. The guide details five building blocks including an inbox, timer, memory, permissions, and an outbound queue to control agent operations.

Also covered byfindgoodai.comIFAIPavitrams
Earlier: