Your local LLM isn’t dumb. Your harness is. (opens in new tab)
A 9B model just fixed a bug that a 30B model couldn’t finish. Same codebase, same prompt, same machine. The 30B had more parameters and…
Read the original articleA 9B model just fixed a bug that a 30B model couldn’t finish. Same codebase, same prompt, same machine. The 30B had more parameters and…
Read the original article