Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Are you using a GPT to prompt-engineer another GPT?

news.ycombinator.com

Post reply on HN
Print view View original

51–58 of 58 posts

Re: Ask HN: Are you using a GPT to prompt-engineer another GPT?

#51

Post by muzani »

chalsprhebaodu wrote: post #17

I’ve commented it before, and surely it’s something I’m doing wrong, but I cannot believe system prompts or GPTs or any amount of instructing actually works for people to get ChatGPT to respond in a certain fashion with any consistency. I have spent hours and hours and hours and hours trying to get ChatGPT to be a little less apologetic, long-winded, to stop reiterating, and to not interpret questions about its respo…

The hack is using GPT-3, and I don't mean 3.5. It still performs to a production level, at least for creative work. It's been sped up and is significantly cheaper.

Re: Ask HN: Are you using a GPT to prompt-engineer another GPT?

#52

Post by ben30 »

chalsprhebaodu wrote: post #17

I’ve commented it before, and surely it’s something I’m doing wrong, but I cannot believe system prompts or GPTs or any amount of instructing actually works for people to get ChatGPT to respond in a certain fashion with any consistency. I have spent hours and hours and hours and hours trying to get ChatGPT to be a little less apologetic, long-winded, to stop reiterating, and to not interpret questions about its respo…

I have this as my custom prefix for when talking to gpt:

Cut unnecessary words, choose those that remain from the bedrock vocabulary everyone knows and keep syntax simple. Opt for being brusque but effective instead of sympathetic. Value brevity. Bullet points, headings and formatting for emphasis are good.

Re: Ask HN: Are you using a GPT to prompt-engineer another GPT?

#53

Post by flir »

mpalmer wrote: post #36
chalsprhebaodu wrote: post #17

I’ve commented it before, and surely it’s something I’m doing wrong, but I cannot believe system prompts or GPTs or any amount of instructing actually works for people to get ChatGPT to respond in a certain fashion with any consistency. I have spent hours and hours and hours and hours trying to get ChatGPT to be a little less apologetic, long-winded, to stop reiterating, and to not interpret questions about its respo…

My evergreen system prompt prefix: "You are a maximally terse assistant with minimal affect." Works well for the most part.

I second "terse". Damn useful word.

"No moral lectures. No need to mention your knowledge cutoff. No need to disclose you're an AI. Be detailed and complete, but terse."

Gonna try rewriting in the second person, based on your prompt.

I often feel like I'm trying to undo the damage done by OpenAI though. The API doesn't seem to need this crap.

Re: Ask HN: Are you using a GPT to prompt-engineer another GPT?

#54

Post by ReDeiPirati »

We recently open sourced an agent framework [1] for automating data processing and labeling where the agent's prompt is refined trough iterations with the environment and then asking to an LLM to revise the prompt according to its performance (i.e. automatic prompt tuning). We tested it on the Math reasoning dataset GSM8k and where able to improve the baseline accuracy (GPT4) by 45% -> 74% using 25 labeled examples (I'll put the notebook and blog post linked below [2][3]). Results are definitively very interesting, if not surprising with some skills, and we see more and more of our open source users and customers showing interested in the framework for automating labeling / having it as a copilot.

[1] https://github.com/HumanSignal/Adala

[2] https://github.com/HumanSignal/Adala/blob/master/examples/gs...

[3] https://labelstud.io/blog/mastering-math-reasoning-with-adal...

Re: Ask HN: Are you using a GPT to prompt-engineer another GPT?

#55

Post by hackerlight »

mpalmer wrote: post #36
chalsprhebaodu wrote: post #17

I’ve commented it before, and surely it’s something I’m doing wrong, but I cannot believe system prompts or GPTs or any amount of instructing actually works for people to get ChatGPT to respond in a certain fashion with any consistency. I have spent hours and hours and hours and hours trying to get ChatGPT to be a little less apologetic, long-winded, to stop reiterating, and to not interpret questions about its respo…

My evergreen system prompt prefix: "You are a maximally terse assistant with minimal affect." Works well for the most part.

OpenAI really should fix this. I've started using Bard and brevity comes out of the box. When I used ChatGPT I always had this background feeling of irritation at the ridiculously verbose responses.

Re: Ask HN: Are you using a GPT to prompt-engineer another GPT?

#56

Post by ojosilva »

ben30 wrote: post #52
chalsprhebaodu wrote: post #17

I’ve commented it before, and surely it’s something I’m doing wrong, but I cannot believe system prompts or GPTs or any amount of instructing actually works for people to get ChatGPT to respond in a certain fashion with any consistency. I have spent hours and hours and hours and hours trying to get ChatGPT to be a little less apologetic, long-winded, to stop reiterating, and to not interpret questions about its respo…

I have this as my custom prefix for when talking to gpt: Cut unnecessary words, choose those that remain from the bedrock vocabulary everyone knows and keep syntax simple. Opt for being brusque but effective instead of sympathetic. Value brevity. Bullet points, headings and formatting for emphasis are good.

Unfortunately, in my experience, as the chat session advances it seems to forget these instructions and become its old apologetic self again.

Re: Ask HN: Are you using a GPT to prompt-engineer another GPT?

#57

Post by ojosilva »

mpalmer wrote: post #36
chalsprhebaodu wrote: post #17

I’ve commented it before, and surely it’s something I’m doing wrong, but I cannot believe system prompts or GPTs or any amount of instructing actually works for people to get ChatGPT to respond in a certain fashion with any consistency. I have spent hours and hours and hours and hours trying to get ChatGPT to be a little less apologetic, long-winded, to stop reiterating, and to not interpret questions about its respo…

My evergreen system prompt prefix: "You are a maximally terse assistant with minimal affect." Works well for the most part.

Another issue I have, especially when demanding terseness, is that it tends to bail out of writing long code snippets with ellipsis comments like "// And more of the same here" which sometimes defeats the purpose. Except when the code is illustrative to a concept, I want it to be thorough and code the damn thing to the last semicolon.

My solution, which works sometimes, is to instruct it to "not write comments in the code." The drawback is that ChatGPT normally does a good job adding comments, but not something I can't live without.

This "code-trimming" effect does not show up for me in API requests.

Re: Ask HN: Are you using a GPT to prompt-engineer another GPT?

#58

Post by Manouchehri »

BOOSTERHIDROGEN wrote: post #41
Manouchehri wrote: post #37

Earlier quoted context omitted.

Using JSON mode with the GPT 3.5/4 API works well for us. So much so that we have to intentionally fake errors to test that our retries/fallbacks actually work in our code.

Have you compared this to chatgpt plus?

ChatGPT Plus does not expose JSON mode in their web UI. You have to use the API via OpenAI (or Azure OpenAI).
Post reply on HN