tools news, stories and analysis

Claude Code auto mode block rate for dangerous commands: human reviewers caught 13.6 percent, auto mode caught 89 percent. Prompt injection attack success rate was 0 percent for Claude models in auto mode versus 5.83 percent for GPT-5.6 Sol in Codex Auto-review.

Claude Code auto mode becomes default on August 14

Claude Code auto mode runs commands without per-step permission. It becomes the default August 14, 2026 for Pro, Max, and Team plans.

Lars Cornelissen · Aug 9, 2026

Abstract bar visualization of AI provider entries in the AI agent guide. In 2025, ChatGPT, Claude, and Gemini each had 1 chat mode recommended. In 2026, ChatGPT has 2 agent modes, Claude has 2 agent modes, and Gemini has 0. The AI agent guide shows ChatGPT and Claude leading with 2 agent modes each while Gemini dropped to 0.

AI for dummies

Your AI agent guide: which AI to use for tasks in 2026

This AI agent guide maps the shift from chat to agents. ChatGPT Work and Claude Cowork now lead for real work, while Gemini has dropped off the list.

Lars Cornelissen · Jul 29, 2026

Bar chart of local AI decode speeds on Apple Silicon. Qwen 3.6 27B on M5 Max: 28 tok/s baseline, 63 tok/s with MTPLX MTP, a 2.24x speedup.

AI for dummies

How MTPLX v2 makes local AI on Mac twice as fast

MTPLX v2 uses multi-token prediction to run local AI on Apple Silicon Macs up to 2.24x faster. Here is what beginners need to know.

Lars Cornelissen · Jul 9, 2026

Abstract data-art visualization of GenieX local LLM inference on Snapdragon showing token throughput with Gemma 4 26B at 20 tok/s and Qwen 3.6 27B at 10 tok/s

AI for dummies

GenieX: Qualcomm's local LLM runtime for Snapdragon laptops

GenieX is Qualcomm's runtime for running LLMs locally on Snapdragon laptops and phones. Early users report 20 tokens per second on a 26B model.

Lars Cornelissen · Jul 5, 2026

Scatter of about 17 dictionary concepts plotted by cosine distance from a seed word, clustered into a near band of banned cliches and a middle band of surprising-but-related lenses the generator is allowed to use.

AI

How to make an LLM escape its own prior with geometry

Novel Search Space breaks an LLM out of its prior by ranking 80,000 dictionary words by embedding distance, banning the obvious neighbours, and forcing the model to brainstorm only from a surprising-but-related band.

Lars Cornelissen · Jun 27, 2026