Tag generative-ai
21 bookmarks have this tag.
2026-01-29
The Five Levels: from Spicy Autocomplete to the Dark Factory
simonwillison.net/2026/Jan/28/the-five-levelsDan Shapiro proposes a five level model of AI-assisted programming, inspired by the five (or rather six, it's zero-indexed) levels of driving automation. Spicy autocomplete, aka original GitHub Copilot or …
2026-01-04
Helping people write code again
simonwillison.net/2026/Jan/4/coding-again#atom-everything2025-12-28
Superpowers: How I'm using coding agents in October 2025
simonwillison.net/2025/Oct/10/superpowers#atom-everything2025-12-10
The Normalization of Deviance in AI
simonwillison.net/2025/Dec/10/normalization-of-deviance#atom-everything2025-12-09
Quoting Claude
simonwillison.net/2025/Dec/9/claude#atom-everything2025-10-27
GenAI Image Editing Showdown
simonwillison.net/2025/Oct/26/genai-image-editing-showdown#atom-everything2025-10-16
NVIDIA DGX Spark + Apple Mac Studio = 4x Faster LLM Inference with EXO 1.0
simonwillison.net/2025/Oct/16/nvidia-dgx-spark-apple-mac-studio#atom-everything2025-10-09
Armin Ronacher: 90%
simonwillison.net/2025/Sep/29/armin-ronacher-90#atom-everything2025-10-02
Daniel Stenberg's note on AI assisted curl bug reports
simonwillison.net/2025/Oct/2/curl#atom-everything2025-09-14
Quoting Matt Webb
simonwillison.net/2025/Sep/12/matt-webb#atom-everything2025-08-20
llama.cpp guide: running gpt-oss with llama.cpp
simonwillison.net/2025/Aug/19/gpt-oss-with-llama-cpp#atom-everything2025-08-15
Introducing Gemma 3 270M: The compact model for hyper-efficient AI
simonwillison.net/2025/Aug/14/gemma-3-270m#atom-everything2025-08-13
simonw/codespaces-llm
simonwillison.net/2025/Aug/13/codespaces-llm#atom-everything2025-08-05
Qwen-Image: Crafting with Native Text Rendering
simonwillison.net/2025/Aug/4/qwen-image#atom-everything2025-07-08
Become a command-line superhero with Simon Willison's llm tool
simonwillison.net/2025/Jul/7/become-a-command-line-superhero-with-simon-willisons-llm-tool#atom-everything2025-06-30
How to Fix Your Context
simonwillison.net/2025/Jun/29/how-to-fix-your-context#atom-everything2025-06-21
Magenta RealTime: An Open-Weights Live Music Model
simonwillison.net/2025/Jun/20/magenta-realtime#atom-everythingAgentic Misalignment: How LLMs could be insider threats
simonwillison.net/2025/Jun/20/agentic-misalignment#atom-everything2025-06-19
A CLI for on-device speech transcription using Speech.framework on macOS 26.
github.com/finnvoor/yapWhat stood out above all else was Yap’s speed. By harnessing SpeechAnalyzer and SpeechTranscriber on-device, the command line tool tore through the 7GB video file a full 55% faster than MacWhisper’s Large V3 Turbo model, with no noticeable difference in transcription quality.