> Below is an example of Kimi K3 using this for Unsplash, a free images provider that models commonly use to find hero visuals and other filler images. On top is the chain-of-thought reasoning, and below is the Unsplash CDN image that the model thought about when it generated the ID.

I wonder how many image ids it memorized and whether it would always use those or search for new images?

▲

supriyo-biswas 2 days ago | parent [-]

I would hope that they really didn't move in the direction of having the model memorize image IDs, as that could be easily replaced with an embedding-based image search tool call.

Although, it is possible that it was unintentional as the model was RLHF'ed into memorizing images.

	▲	dannyw a day ago \| parent [-]
		If you train on any form of HTML, or any code that includes URLs, your model is going to learn them somehow. Stripping URLs would certainly break some code, and also train the model with unhelpful behavior. You want your coding model to write real URLs, not write "return redirect(<\|URL_STRIPPED\|>)".