Repeating my previous posts for newcoomers:
guize... we got to try training a model on this, right?
I'm tempted to risk getting b& from yet another cloud provider by grabbing the $200 plan and generating as many responses as I can.
These aren't the real reasoning traces but it sure as fuck looks like it'd still work well enough.
$ curl -X POST http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer test-key" -d '{
"model": "gpt-5",
"messages": [{"role": "user", "content": "Tell me a joke"}]
}'
{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"<think>I\u2019m looking to keep things simple and deliver a single joke as requested. No tools are needed, and I want to maintain a friendly tone. \n\nI\u2019m considering a couple of options\u2014like, \u201cI told my wife she was drawing her eyebrows too high. She looked surprised.\" But then there's a better tech joke: \u201cWhy do programmers prefer dark mode? Because light attracts bugs.\u201d \n\nThis sounds clever and safe! So, I\u2019ll go with that as my final answer.</think>Why do programmers prefer dark mode? Because light attracts bugs.","role":"assistant"}}],"created":1763595363,"id":"resp_0eeac847c94a6a5701691e546344f0819bae0f489146835a89","model":"gpt-5","object":"chat.completion","usage":{"completion_tokens":146,"prompt_tokens":5015,"total_tokens":5161}}
>>107266615
au contraire, people were talking how google originally showed the gemini 2.5 on aistudio traces but now shows a chatgpt web interface style summary (I remember it outputting more realistic looking traces as well).
But who knows, maybe this is because the gemma scandal and they can be gotten through API, I'm not sure.
