alt Hacker Newsbut a good combination of prompt, harness and model will easily close that gap. a more advanced (but equivalent) form of grep could also offer fuzzy matching/levenshtein distance function to augment that.
Replies
c-hendricks • yesterday at 9:56 PM
This sounds like AOT vs JIT weights.
It will, but it does so by burning tokens. I'm sure you've also seen the output of an overly eager grep by an LLM.
I think we're verging on the point where people will care more about the most token-efficient ways to do a task than the lowest human effort version. Humans are expensive, humans using half as many tokens are cheaper.