News for hackers. Stuff that matters.
Re:Claude's memory architecture is the opposite of ChatGPT's by lostdog on Thursday September 11, 2025 @06:00PM (#45216554)
There is no such thing as a good flow for showing sponsored items in an LLM workflow.

The point of using an LLM is to find the thing that matches your preferences the best. As soon as the amount of money the LLM company makes plays into what's shown, the LLM is no longer aligned with the user, and no longer a good tool.

Re:Claude's memory architecture is the opposite of ChatGPT's by agar on Friday September 12, 2025 @01:20AM (#45218850)
Same can be said for search. And your statement is provably correct, depending on the definition of "good tool."

But it's not only money's influence on the company, it's also money's influence on the /data/ underlying the platform that undermines the tool.

Once financial incentives are in place, what will be the AI equivalent of review bombing, SEO, linkjacking, google bombing, and similar bad behaviors that undermine the quality of the source data?