News Score: Score the News, Sort the News, Rewrite the Headlines

Claude 3.7 Sonnet, extended thinking and long output, llm-anthropic 0.14

25th February 2025 Claude 3.7 Sonnet is a very interesting new model. I released llm-anthropic 0.14 last night adding support for the new model’s features to LLM. I learned a whole lot about the new model in the process of building that plugin. The base Claude 3.7 Sonnet model mostly feels like an incremental improvement over the excellent Claude 3.5 Sonnet. It benchmarks better and my vibe checks so far are good: it writes excellent code across Python and JavaScript and seems to do everything 3...

Read more at simonwillison.net

© News Score  score the news, sort the news, rewrite the headlines