Related Posts
The Two Pillars of Post-training: Reinforcement Learning and Supervised Fine-Tuning
- admin
- August 12, 2026
- 1 min read
- 0
This is the second article in Sharon Zhou’s post-training series. Read part 1 here. In the first post of this series, you learned how post-training closed the fundamental gap in usability of LLMs by making them behave in a certain way. In this post, you’ll explore specific techniques you can use to change a model’s […]
German AI consortium releases Soofi S, an open 30B model that tops benchmarks in both English and German
- admin
- July 13, 2026
- 1 min read
- 0
A German research consortium has released Soofi S 30B-A3B, an open language model trained entirely on Deutsche Telekom’s cloud infrastructure in Munich. The model uses an efficient hybrid architecture that activates only a fraction of its 31.6 billion parameters per token, keeping throughput steady even at very long contexts. With a training dataset deliberately weighted […]
Young adult dies of meningococcal disease in Waikato
- admin
- August 16, 2026
- 1 min read
- 0
Health NZ urges people to learn the symptoms of the disease and get vaccinated.
Kim Dotcom’s first major interview since stroke shows speech heavily impacted
- admin
- August 8, 2026
- 1 min read
- 0
The internet mogul has worked hard at rehabilitation since his life-changing 2024 stroke.