I am not an LLM guy but as far as I understand, RLHF did a good job converting a base model into a chat model (instruct based), a chat/base model into a thinking model.

Both of these examples are about the nature of the response, and the content they use to fill the response. There are so many differnt ways still pending to see how these can be filled.

Generating an answer step by step and letting users dive into those steps is one of the ways, and RLHF (or the similar things which are used) seems a good fit for it.

Prompting feels like a temporary solution for it like how "think step by step" was first seen in prompts.

Also, doing RLHF/ post training to change these structures also make it moat/ and expensive. Only the AI labs can do it

It would be wondeful if some of the tools the projects uses are exposed to build on. Like the tools related to AST, finding definitions, and many more

Teachers play such an important rule. They have to swallow the pill that the common narrative is that cause they didn’t do whatever they are teaching hence they teach

We need safe bike lanes. If my city has it, I’ll quickly jump the gun to make an investment. To add on top of it, let’s have some theft safety as well by building garages or having an airbnb equivalent of parking in private places. But as I think about these they feel like a child wishing for a gift on Christmas.