Analecta Curiosa

Clear
429 articles
36 since yesterday
My 2.5 year old laptop can write Space Invaders in JavaScript now, using GLM-4.5 Air and MLX
Using GitHub Spark to reverse engineer GitHub Spark
ChatGPT agent’s user-agent
Reverse engineering some updates to Claude
The surprise deprecation of GPT-4o for ChatGPT consumers
GPT-5: Key characteristics, pricing and model card
OpenAI’s new open weight (Apache 2) models are really good
Qwen3-4B-Thinking: “This is art—pelicans don’t ride bikes!”
My Lethal Trifecta talk at the Bay Area AI Security Meetup
The Summer of Johann: prompt injections as far as the eye can see
Open weight LLMs exhibit inconsistent performance across providers
LLM 0.27, the annotated release notes: GPT-5 and improved tool calling
GPT-5 Thinking in ChatGPT (aka Research Goblin) is shockingly good at search
V&A East Storehouse and Operation Mincemeat in London
My review of Claude’s new Code Interpreter, released under a very confusing name
Recreating the Apollo AI adoption rate chart with GPT-5, Python and Pyodide
Designing agentic loops
Claude Sonnet 4.5 is probably the “best coding model in the world” (at least for now)
Vibe engineering
OpenAI DevDay 2025 live blog

Filters & Sorting

Clear All