|
| ▲ | cdrini 4 days ago | parent | next [-] |
| The best research I've seen on this is: - Threatening or tipping a model generally has no significant effect on benchmark performance. - Prompt variations can significantly affect performance on a per-question level. However, it is hard to know in advance whether a particular prompting approach will help or harm the LLM's ability to answer any particular question. https://arxiv.org/abs/2508.00614 |
| |
| ▲ | SV_BubbleTime 4 days ago | parent [-] | | That 100% tracks expectation if your technical knowledge exceeds past “believer”. Now… for fun. Look up “best prompting” or “the perfect prompt” on YouTube. Thousands of videos “tips” and “expect recommendations” that are bordering the arcane. | | |
| ▲ | theshrike79 3 days ago | parent [-] | | The worst people are just writing D&D Character backstories as agent prompts: "You are a world-class developer in <platform>..." type of crap. | | |
| ▲ | SV_BubbleTime 3 days ago | parent [-] | | Haha, at least one this… I could make an excuse, that if I’m juggling prompts around, one that starts “You are a copy writer…” vs “You are an editor that…” lets me separate them with natural language vs some historically dubious file system disorganization. |
|
|
|
|
| ▲ | diggan 4 days ago | parent | prev | next [-] |
| > Better results if you… tip the AI, offer it physical touch, you need to say the words “go slow and take a deep breath first”… I'm not saying I've proven it or anything, but it doesn't sound far-fetched that a thing that generates new text based on previous text, would be affected by the previous text, even minor details like using ALL CAPS or just lowercase, since those are different tokens for the LLM. I've noticed the same thing with what exact words you use. State a problem as a lay/random person, using none of the domain words for things, and you get a worse response compared to if you used industry jargon. It kind of makes sense to me considering how they work internally, but happy to be proven otherwise if you're sitting on evidence either way :) |
| |
| ▲ | SV_BubbleTime 4 days ago | parent [-] | | We all agree that prompts are affected by tokens. The issue is that you can’t know if you are positively or negatively effecting because there is no real control. And the effect could switch between prompts. |
|
|
| ▲ | kachapopopow 4 days ago | parent | prev | next [-] |
| I tell my agent to off it self every couple of hours, it's definitely placebo as you're just introducing noise which might or might not be good. Adding hmm, <prompt> has been my goto for a bit if I want it to force to give me different results cause it appears to trigger some latent regions of the llms. |
| |
| ▲ | SV_BubbleTime 4 days ago | parent [-] | | This seems to be exactly what I’m talking about though. We made a completely subjective system and now everyone has completely subjective advice about what works. I’m not saying introducing noise isn’t a valid option, just doing it in ‘X’ or ‘y’ method as dogma is straight bullshit. | | |
| ▲ | kachapopopow 19 hours ago | parent [-] | | I was thinking about this and I disagree, if you can force "better" paths for programming based on the prompt I think that might as well give you better results. |
|
|
|
| ▲ | throwawa14223 4 days ago | parent | prev [-] |
| This is one of many reasons that I believe the value of current AI tech is zero if not negative. |
