← All Tags
# benchmarks → reinforcement-learning → llm → open-source

1 link tagged with all of: benchmarks + reinforcement-learning + llm + open-source

Click any tag below to further narrow down your results

+ deepseek (1)

Links

Thread by @suchenzang on Thread Reader App

This article discusses advancements in the Deepseek model, highlighting reduced attention complexity and innovations in reinforcement learning training. It also critiques the assumptions surrounding open-source large language models and questions the benchmarks used to evaluate their performance.
Saved by tldr-importer · Last saved February 14, 2026 · 3 min read
+ deepseek llm ✓ reinforcement-learning ✓ benchmarks ✓ open-source ✓