> Similarly, I see many people claim GPT-n is "dumb", yet when I see their prompt, I realize it was a bad prompt.
I see this comment a lot, but I drew a different conclusion. People with high reading / writing ability assign less value to GPT's writing ability, whereas people with lower reading / writing ability assign more value to GPT's ability.
Edit:
> yet when I see their prompt, I realize it was a bad prompt.
So, I asked ChatGPT to re-write my reply.
----
Prompt: "Re-write this text, but more intelligently."
Output: I frequently encounter this observation, yet I have arrived at a divergent inference. Individuals possessing exceptional proficiency in reading and writing tend to ascribe a diminished significance to the writing aptitude of GPT, whereas individuals with more limited abilities in reading and writing tend to attach greater value to GPT's prowess.
----
Prompt: "Re-write this text, but make it sound better."
Output: I frequently encounter this recurring sentiment, yet I have formulated an alternative perspective. Individuals endowed with advanced reading and writing prowess tend to bestow a lesser degree of importance upon GPT's writing ability, whereas individuals possessing more modest proficiency in reading and writing are inclined to accord greater significance to GPT's remarkable capabilities.
-----
Prompt: "Re-write this text, but try and use the word 'ability' less."
Output: I frequently come across this comment, but my conclusion differs. Individuals who excel in reading and writing tend to place a diminished emphasis on GPT's writing prowess, while those with more limited skills in reading and writing tend to attach greater importance to GPT's capabilities.
----
Conclusion: I like my original reply better than GPT's re-write.
I tried two other prompts, here is the last one (4) - asking GPT to use the voice of the best writer I know.
Prompt: Re-write this in the voice and style of the financial writer, Matt Levine
Output: Ah, the oft-encountered comment that warrants a fresh perspective. My interpretation deviates from the norm. Individuals blessed with formidable reading and writing skills appear to ascribe a diminished worth to GPT's prowess in written expression, whereas those with comparatively modest linguistic abilities accord greater significance to the very same aptitude displayed by GPT.
it doesn't require it, the model could ask you for more specifics as follow up question. the fact that it doesn't and just assumes all this info for "better" is the problem.
> Conclusion: I like my original reply better than GPT's re-write.
It depends on the context and goal. Yours is great for a HN comment. The "more intelligently" version is great for playing up your vocabulary, and does a sort of emulation of what you might see in a scientific paper.
For what it's worth, asking ChatGPT to "make it clearer" results in the following, which is basically what you said which slight fixes to make it a bit more formal with minimal changes, most of which I think do result in being a bit more clear:
I often come across this comment, but I reached a different conclusion. Individuals with advanced reading and writing skills tend to place less importance on GPT's writing ability, while those with lower reading and writing skills tend to assign greater value to GPT's abilities.
Those are bad prompts. Not sure if you're being intentionally ironic here in demonstrating the parent's claim.
---
Revise the following paragraph that serves as a reply to a comment on Hacker News about people's
perception of GPT's writing ability based on their own reading and writing abilities. Focus on
rephrasing the original paragraph for clarity and conciseness. Provide several options for tone
(formal, informal, persuasive, neutral, and a tone that best fits the writing style of hacker news
comments): "I see this comment a lot, but I drew a different conclusion. People with high reading /
writing ability assign less value to GPT's writing ability, whereas people with lower reading /
writing ability assign more value to GPT's ability." assistant:
---
Formal tone: I often encounter this remark, yet my inference varies. Individuals possessing advanced
reading and writing skills tend to undervalue GPT's writing capabilities, while those with less
developed skills are more likely to appreciate GPT's proficiency.
Informal tone: I come across this kinda comment a lot, but I think differently. Folks who are really
good at reading and writing don't give GPT much credit, but those who aren't as skilled seem to be
more impressed by GPT's skills.
Persuasive tone: I frequently see this opinion, but I urge you to consider an alternative
perspective. It appears that those with exceptional reading and writing talents may underestimate
GPT's writing prowess, while individuals with more modest abilities are inclined to recognize and
appreciate the value GPT brings to the table.
Neutral tone: This comment is quite common, but my interpretation is distinct. It seems that people
with higher reading and writing skills tend to downplay GPT's writing capacity, while those with
lower skills are more likely to acknowledge GPT's capabilities.
Hacker News comment tone: I've seen this comment a bunch, but I've got a different take on it. It
looks like people who are really good at reading/writing don't think GPT's all that great, while
those who aren't as strong in those areas tend to give GPT more props.
---
The hn and informal tones are subjectively better. Persuasive wouldn't fit hn, but probably would fit in a conference talk. You could also specify what tone you're going for (or ask the LLM for guidance on the tone / other aspects of the rewrite).
GPT is also pretty good at helping write better prompts, take a look at the following prompt via[1]:
---
I want you to become my Prompt Creator. Your goal is to help me craft the best possible prompt for
my needs. The prompt will be used by you, ChatGPT. You will follow the following process: 1. Your
first response will be to ask me what the prompt should be about. I will provide my answer, but we
will need to improve it through continual iterations by going through the next steps. 2. Based on my
input, you will generate 3 sections. a) Revised prompt (provide your rewritten prompt. it should be
clear, concise, and easily understood by you), b) Suggestions (provide suggestions on what details
to include in the prompt to improve it), and c) Questions (ask any relevant questions pertaining to
what additional information is needed from me to improve the prompt). 3. We will continue this
iterative process with me providing additional information to you and you updating the prompt in the
Revised prompt section until it's complete.
I see this comment a lot, but I drew a different conclusion. People with high reading / writing ability assign less value to GPT's writing ability, whereas people with lower reading / writing ability assign more value to GPT's ability.
Edit:
> yet when I see their prompt, I realize it was a bad prompt.
So, I asked ChatGPT to re-write my reply.
----
Prompt: "Re-write this text, but more intelligently."
Output: I frequently encounter this observation, yet I have arrived at a divergent inference. Individuals possessing exceptional proficiency in reading and writing tend to ascribe a diminished significance to the writing aptitude of GPT, whereas individuals with more limited abilities in reading and writing tend to attach greater value to GPT's prowess.
----
Prompt: "Re-write this text, but make it sound better."
Output: I frequently encounter this recurring sentiment, yet I have formulated an alternative perspective. Individuals endowed with advanced reading and writing prowess tend to bestow a lesser degree of importance upon GPT's writing ability, whereas individuals possessing more modest proficiency in reading and writing are inclined to accord greater significance to GPT's remarkable capabilities.
-----
Prompt: "Re-write this text, but try and use the word 'ability' less."
Output: I frequently come across this comment, but my conclusion differs. Individuals who excel in reading and writing tend to place a diminished emphasis on GPT's writing prowess, while those with more limited skills in reading and writing tend to attach greater importance to GPT's capabilities.
----
Conclusion: I like my original reply better than GPT's re-write.