- January - 9 entries, 53 links, 29 quotes
- Ending a year long posting streak
- I still don't think companies serve you ads based on spying through your microphone
- Weeknotes: Starting 2025 a little slow
- My AI/LLM predictions for the next 1, 3 and 6 years, for Oxide and Friends
- DeepSeek-R1 and exploring DeepSeek-R1-Distill-Llama-8B
- Six short video demos of LLM and Datasette projects
- Anthropic's new Citations API
- A selfish personal argument for releasing code as Open Source
- OpenAI o3-mini, now available in LLM
- February - 7 entries, 48 links, 16 quotes
- Using pip to install a Large Language Model that's under 100MB
- URL-addressable Pyodide Python environments
- Run LLMs on macOS using llm-mlx and Apple's MLX framework
- LLM 0.22, the annotated release notes
- Claude 3.7 Sonnet, extended thinking and long output, llm-anthropic 0.14
- Initial impressions of GPT-4.5
- Structured data extraction from unstructured content using LLM schemas
- March - 11 entries, 59 links, 18 quotes, 1 note
- Hallucinations in code are the least dangerous form of LLM mistakes
- Notes from my Accessibility and Gen AI podcast appearance
- I built an automaton called Squadron
- What's new in the world of LLMs, for NICAR 2025
- Here's how I use LLMs to help me write code
- Notes on Google's Gemma 3
- Adding AI-generated descriptions to my tools collection
- Not all AI-assisted programming is vibe coding (but vibe coding rocks)
- Calling a wrap on my weeknotes
- New audio models from OpenAI, but how much can we rely on them?
- Putting Gemini 2.5 Pro through its paces
- April - 12 entries, 50 links, 26 quotes, 12 notes
- Initial impressions of Llama 4
- Long context support in LLM 0.24 using fragments and template plugins
- Model Context Protocol has prompt injection security problems
- CaMeL offers a promising new direction for mitigating prompt injection attacks
- GPT-4.1: Three new million token input models from OpenAI, including their cheapest model yet
- Image segmentation using Gemini 2.5
- Maybe Meta's Llama claims to be open source because of the EU AI act
- AI assisted search-based research actually works now
- Exploring Promptfoo via Dave Guarino's SNAP evals
- Watching o3 guess a photo's location is surreal, dystopian and wildly entertaining
- Qwen 3 offers a case study in how to effectively release a model
- Understanding the recent criticism of the Chatbot Arena
- May - 11 entries, 59 links, 14 quotes, 21 notes
- Two publishers and three authors fail to understand what "vibe coding" means
- Feed a video to a vision LLM as a sequence of JPEG frames on the CLI (also LLM 0.25)
- Saying "hi" to Microsoft's Phi-4-reasoning
- Trying out llama.cpp's new vision support
- Building software on top of Large Language Models
- I really don't like ChatGPT's new memory dossier
- Live blog: Claude 4 launch at Code with Claude
- Highlights from the Claude 4 system prompt
- Large Language Models can run tools in your terminal with LLM 0.26
- Talking AI and jobs with Natasha Zouves for News Nation
- How often do LLMs snitch? Recreating Theo's SnitchBench with LLM
- June - 1 entry, 8 links, 3 quotes, 2 notes