1509 related articles
Deep DivesOpenAI's GPT-5.5 model collectively outputs 'goblin' vocabulary. Official technical blog reveals the root cause: reward signal generalization in reinforcement learning.
Deep DivesDeep analysis of Simon Willison's LLM Python library 0.32a0 alpha: message sequences, streaming typed parts, tool calling, and the design philosophy behind backward-compatible refactoring.
TutorialsSimon Willison built a full-stack iNaturalist observation aggregation project on his phone while camping, using Claude Code, Python CLI, Git Scraping, and auto-generated frontend.
Tech FrontiersThe llm CLI tool releases version 0.32a1, fixing a critical bug where tool-calling conversations couldn't be properly restored from the SQLite database.
TutorialsDeep dive into Unsloth: fine-tune and run Gemma 4, Qwen3.6, and DeepSeek locally via Web UI. 70% less VRAM, 5× faster — consumer GPUs welcome.
Tech FrontiersOpenAI Codex CLI 0.128.0 adds the /goal command, implementing an agentic loop via prompt engineering that keeps executing until the goal is met or the token budget runs out.
TutorialsOllama is a 170K-star open source tool for local LLM deployment. Run DeepSeek, Qwen, Kimi-K2.5, GLM-5 and more with one command. Learn its advantages and setup.
Tech FrontiersA GitHub repo with 40K stars has leaked system prompts from ChatGPT, Claude, Gemini, Grok, and Perplexity. Here's what it reveals about AI security.
Deep DivesA deep dive into Gemini CLI, Google's official open-source AI agent for the terminal. Integrates Gemini models directly into your command line. 100K GitHub Stars.