A bunch of useful stuff in this LLM alpha, but the most important detail is this one: This means you can now see the summarized reasoning tokens when you run prompts against an OpenAI model, displayed in a different color to standard error. Use the -R or --hide-reasoning flags if you don't want to see that. This random . If you'd like to report any problems with this post or the blog, please include the following ID with your report: b7c3b98875f4f24267ed65200a331e45-715548

Read the original article