My iPhone 16 Pro Max produces garbage output when running MLX LLMs

kept by eddie feb 02

An iPhone 16 Pro Max produces garbage output when running MLX LLMs due to a hardware defect in the Neural Engine, while an iPhone 15 Pro runs the same code correctly.

MCP Server | AppSignal
AppSignal's MCP server integrates with AI coding tools to deliver real-time performance insights, error tracking, and debugging support directly within developers' editors.
also on #debugging, #developer-tools
Logging sucks | Hacker News
Structured, high-cardinality logs with consistent schemas and correlation IDs improve debugging over traditional unstructured logs in distributed systems.
also on #debugging, #developer-tools
The PR you would have opened yourself
Hugging Face built a Claude Code Skill and test harness that helps contributors port language models from transformers to mlx-lm while preserving code quality and reviewer trust.
also on MLX, #machine-learning, Apple, #developer-tools
GitHub - iannuttall/natter: Fast, local-first dictation for macOS
Natter is a macOS menu bar app that performs local, offline dictation with cleanup for technical terms and voice-taught corrections.
also on MLX, #developer-tools
DSHR's Blog: Distilling The Moat
The article argues that AI companies’ claimed moat from expensive model training is shallow because model distillation allows competitors to cheaply replicate capabilities via repeated API queries.
also on MiniMax, #ai