← Back to context Comment by sedatk 3 months ago Both ChatGPT 4o and Claude 3.5 Sonnet can identify the generated page content as "random words". 2 comments sedatk Reply tlonny 3 months ago Given the size of the training data - I don’t think it would economical to validate all training data with high-end LLM models. sedatk 3 months ago True. Maybe it can be dumbed down to a low-end model specifically for this type of detection.
tlonny 3 months ago Given the size of the training data - I don’t think it would economical to validate all training data with high-end LLM models. sedatk 3 months ago True. Maybe it can be dumbed down to a low-end model specifically for this type of detection.
sedatk 3 months ago True. Maybe it can be dumbed down to a low-end model specifically for this type of detection.
Given the size of the training data - I don’t think it would economical to validate all training data with high-end LLM models.
True. Maybe it can be dumbed down to a low-end model specifically for this type of detection.