# GPT4o doesn't output anything **URL:** \ **Category:** API\ **Tags:** gpt-4\ **Created:** [April 30, 2025, 7:34pm UTC](https://community.openai.com/t/gpt4o-doesnt-output-anything/1247771 "2025-04-30T19:34:12Z")\ **Posts on this page:** 1\ **Showing post:** 3
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [April 30, 2025, 8:47pm UTC](https://community.openai.com/t/gpt4o-doesnt-output-anything/1247771/3 "2025-04-30T20:47:25Z")
This is not an issue of prompting ChatGPT. It is an API concern, performed against trials and gathering statistics. It demonstrates the AI having a decent chance of emitting a stop sequence or other output beyond that desired and instructed. However, one does not need to gather such statistics or make multiple runs. For such a 1-token classification, you can use logprobs, and thus bypass the random sampler and get quite reliable results. Another strategy is to use the logit\_bias parameter on chat completions to promote the desired answers against others. Then finally, use structured outputs so the AI is compelled to write JSON containing that answer. Here’s some code that gives a “boolean” answer, and also shows the logprob of the answer position in a structured output. The sampled answer is also highly affected by developer\_enum\_bias = {“Yes”: -99 , “No”: 0} where you can just put +3 for a bit of promotion. Then those enums are automatically instructed. > [@API parameter logit\_bias is non-functional, not affecting output at all](https://community.openai.com/t/api-parameter-logit-bias-is-non-functional-not-affecting-output-at-all/1102824/3): > > If you look at how the sequence would be encoded: It has the same tokens numbers that would be biased against, the same seen when you expand my results. 3160 and 13022. The logprobs in the results also shows us the strings that are being sampled from at that token position, and each logprob is a token. The GPT-4o tokenizer provided by OpenAI; the Yes/No is still a single token, with or without space after colon: [image] However, the AI can generate whatever tokens its wants, it do… The demonstration of a fault could instead be turned into a classification application. --- _[View the full topic](https://community.openai.com/t/gpt4o-doesnt-output-anything/1247771)._