Local LLMs perform better when you teach them to ask before they answer
xda-developers.com
Local LLMs perform better when you teach them to ask before they answer
1–10 of 14 posts
Re: Local LLMs perform better when you teach them to ask before they answer
#2I'm positively surprised such a little guidance makes such a difference.
is it also useful with the smaller (and cheaper) cloud models?
Re: Local LLMs perform better when you teach them to ask before they answer
#3From the article: "When tasked with coding, writing, editing, or summarizing, ask the user up to three targeted clarifying questions. Proceed with the task once you've received answers and understand the prompt fully. If the task is a simple factual question or conversational message, respond directly."
Re: Local LLMs perform better when you teach them to ask before they answer
#4I started using similar approaches in the sonnet 3.5 era and found them incredibly useful at the time. The frontier lab models have gotten significantly better about their guesses over time, but I still sometimes turn to the technique if my own ideation is only about 80% of the way there, as the LLM's questioning can help me identify the blind spots that need more consideration.
Re: Local LLMs perform better when you teach them to ask before they answer
#5I'm positively surprised such a little guidance makes such a difference. is it also useful with the smaller (and cheaper) cloud models?
Yes. I run local models, Qwen3.6-27B and IMHO the massive level up was the agents and skills files that I've worked on.
Basically I run a flow
Brainstorming > Create Spec > Review Spec* > Create Plans > Review Plan* > Execute Plan (in subagents) > Review Against Plan > Code Review* > Open PR > Finish Plan (marks plan files done)
* Each review step marked with an asterisk uses a paid larger LLM, right now Deepseek V4 Pro. Having it do this catches a lot of small things, and now I'm effectively one shotting any task I give it.
And it's not costing me much at all, just those three reviews. I could use a free model like Gemini but I'm happy with what I've got.
Re: Local LLMs perform better when you teach them to ask before they answer
#6[flagged]
Re: Local LLMs perform better when you teach them to ask before they answer
#7I'm positively surprised such a little guidance makes such a difference. is it also useful with the smaller (and cheaper) cloud models?
Yes. I run local models, Qwen3.6-27B and IMHO the massive level up was the agents and skills files that I've worked on. Basically I run a flow Brainstorming > Create Spec > Review Spec* > Create Plans > Review Plan* > Execute Plan (in subagents) > Review Against Plan > Code Review* > Open PR > Finish Plan (marks plan files done) * Each review step marked with an asterisk uses a paid larger LLM, right now Deepseek V4…
Right on target
Re: Local LLMs perform better when you teach them to ask before they answer
#8Isn't this akin to including all the (missing) keywords from the prompt? YMMV but to me we have found the less optimized way of using LLMs
Re: Local LLMs perform better when you teach them to ask before they answer
#9Absolutely True not only for Local LLMs but for cloud ones too. Clarifying the intention, the type of output we want improves the model's response multiple folds.
Re: Local LLMs perform better when you teach them to ask before they answer
#10This is true even with the SOTA models. Making LLMs ask questions and giving answers is always a good idea. Almost every prompt I write ends with something like this: Unless undoubtedly clear, every decision and action must come from mutual agreement.