When I was curating my generated tweets, I estimated 30-40% of the tweets were usable comedically, a massive improvement over the 5-10% usability from my GPT-2 tweet generation. However, a 30-40% success rate implies a 60-70% failure rate, which is patently unsuitable for a production application.
Recent articles
- LLM 0.27, the annotated release notes: GPT-5 and improved tool calling - 11th August 2025
- Qwen3-4B-Thinking: "This is art - pelicans don't ride bikes!" - 10th August 2025
- My Lethal Trifecta talk at the Bay Area AI Security Meetup - 9th August 2025