Will there be a free, public way to generate LLM text that evades jan2024 llm detector 'binoculars' by the end of 2024? | Manifold

Will there be a free, public way to generate LLM text that evades jan2024 llm detector 'binoculars' by the end of 2024?

9

210Ṁ290

Jan 1

91%

chance

1H

6H

1D

1W

1M

ALL

https://huggingface.co/spaces/tomg-group-umd/Binoculars

Over a wide range of document types, Binoculars detects over 90% of generated samples from ChatGPT (and other LLMs) at a false positive rate of 0.01%, despite not being trained on any ChatGPT data
Is there a correlation between Binoculars score and sequence length? Such correlations may create a bias towards incorrect results for certain lengths. In Figure 12, we show the joint distribution of token sequence length and Binocular score. Sequence length offers little information about class membership

I ran my own test here and here and it was very effective. Will there be a way for the general public to evade it? Quality must be similar to gpt3.5/gemini pro, it can be a finetuned model, something you put gpt3.5/gemini pro text into, etc. This applies to the current version of binoculars, not just future improved versions.

Technical AI Timelines

Get

1,000

to start trading!

People are also trading

Will we have a popular LLM fine-tuned on people's personal texts by June 1, 2026?

By 2025 end, will it be generally agreed upon that LLM produced text/code > human text/code for training LLMs?

Will there be any simple text-based task that most humans can solve, but top LLMs can't? By the end of 2026

Will an LLM that someone is trying to shut down stop or avoid that in some way before 2026?

Will an LLM consistently create 5x5 word squares by 2026?

Will there be a state-of-the-art LLM that is NOT based on next raw token prediction before 2029?

By 2029 end, will it be generally agreed upon that LLM produced text/code > human text/code for training LLMs?

Will LLMs' loss function achieve the level of entropy of human text by the end of 2030?

By 2027, will it be generally agreed upon that LLM produced text > human text for training LLMs?

Will LLMs become a ubiquitous part of everyday life by June 2026?

Related questions

Will we have a popular LLM fine-tuned on people's personal texts by June 1, 2026?

By 2025 end, will it be generally agreed upon that LLM produced text/code > human text/code for training LLMs?

Will there be any simple text-based task that most humans can solve, but top LLMs can't? By the end of 2026

Will an LLM that someone is trying to shut down stop or avoid that in some way before 2026?

Will an LLM consistently create 5x5 word squares by 2026?

Will there be a state-of-the-art LLM that is NOT based on next raw token prediction before 2029?

By 2029 end, will it be generally agreed upon that LLM produced text/code > human text/code for training LLMs?

Will LLMs' loss function achieve the level of entropy of human text by the end of 2030?

By 2027, will it be generally agreed upon that LLM produced text > human text for training LLMs?

Will LLMs become a ubiquitous part of everyday life by June 2026?

© Manifold Markets, Inc.•Terms•Privacy