Was toying with the idea that with everyone vibe coding niche educational sites (this is a claim about myself, not this site) it would be nice if that effort could go into building an auditable library of widgets/ educational resources users could trust.
Disclaimer: my concept is a stalled WIP/ completely vibe coded, but for me it was fun POC of a widget registry that can be served into chats via mcp
100% agree. If the models are so capable that they're advancing math, it doesn't seem like a stretch to expect they should be able to determine with "doing math research" entails and the best way to use their capabilities towards that end. Why do we need to hand hold the models by telling them to do parallel research, keep threads independent, etc.
Because they're not aware of what user wants, and they need to know what expectation is, if it finds out it's a famous open problem it may think informing the user and not trying is best option as average user may not prefer it spending hours when success isn't guaranteed, by telling it to use it's available tools and not stop at partial progress, use subagents for various independent approaches it's allowing LLM to know what it should do and what counts as success. These things do great when goal is well defined.
https://learn.mimmsy.com/
Was toying with the idea that with everyone vibe coding niche educational sites (this is a claim about myself, not this site) it would be nice if that effort could go into building an auditable library of widgets/ educational resources users could trust.
Disclaimer: my concept is a stalled WIP/ completely vibe coded, but for me it was fun POC of a widget registry that can be served into chats via mcp
reply