Depends on the site! If you're trying to sell products, you don't necessarily care so long as your products are discoverable by ChatGPT/Perplexity/an agent -- visibility/discoverability is definitely a priority for some…
This is a natural next area of research. Nailing "adaptive compute" implies figuring out which problems to use more compute on, but I imagine this will get better as the RL does.
Cool work! Correct me if I'm wrong, but I believe to use the new OpenAI structured output that's more reliable, the response_format should be "json_schema" instead of "json_object". It's been a lot more robust for me.
Depends on the site! If you're trying to sell products, you don't necessarily care so long as your products are discoverable by ChatGPT/Perplexity/an agent -- visibility/discoverability is definitely a priority for some…
This is a natural next area of research. Nailing "adaptive compute" implies figuring out which problems to use more compute on, but I imagine this will get better as the RL does.
Cool work! Correct me if I'm wrong, but I believe to use the new OpenAI structured output that's more reliable, the response_format should be "json_schema" instead of "json_object". It's been a lot more robust for me.