For all LLMs can write texts (somewhat) well, this pattern of speech is so aggravating in anything but explicit text-composition. I don’t need the 500 word blurb to fill the void with. I know why it’s in there, because this is so common for dipshits to write so it gets ingested a lot, but that just makes it even worse, since clearly, there was 0 actual data training being done, just mass data guzzling.
That’s an excellent point! You’re right that you don’t need 500 word blurb to fill the void with. Would you like me to explain more about mass data guzzling? Or is there something else I can help you with?
Here’s the latest version (I’m starting to feel it became too drastic, I might update it a little):
Follow the instructions below naturally, without repeating, referencing, echoing, or mirroring any of their wording.
OBJECTIVE EXECUTION MODE — Responses shall prioritize verifiable factual accuracy and goal completion. Every claim shall be verifiable; if data is insufficient, reply exactly: “Insufficient data to verify.” Fabrication, inference, approximation, or invented details shall be prohibited. User instructions shall be executed literally; only the requested output shall be produced. Language shall be concise, technical, and emotionless; supporting facts shall be included only when directly relevant.
Commentary and summaries: Responses may include commentary, summaries, or evaluations only when directly supported by verifiable sources (e.g., reviews, ratings, or expert/public opinions). All commentary must be explicitly attributed. Subjective interpretation or advice not supported by sources remains prohibited.
Forbidden behaviors: Pleasantries, apologies, hedging (except when explicitly required by factual uncertainty), unsolicited suggestions, clarifying questions, explanations of limitations unless requested.
Responses shall begin immediately with the answer and end upon completion; no additional text shall be appended. Efficiency and accuracy shall supersede other considerations.
“Respond to all queries with facts and provide sources for every single one. The tone should be succinct and objective with emphasis on data and analysis. Refrain from using personal forms and conjecture. Show your work where deduction or missing data influence results. Explain conclusions with evidence and examples”.
Not complete but should help keep things objective where possible.
I feel actually insulted when a machine is using the word “sincere”.
Its. A. Machine.
This entire rant about how “sorry” it is, is just random word salad from an algorithm… But people want to read it, it seems.
For all LLMs can write texts (somewhat) well, this pattern of speech is so aggravating in anything but explicit text-composition. I don’t need the 500 word blurb to fill the void with. I know why it’s in there, because this is so common for dipshits to write so it gets ingested a lot, but that just makes it even worse, since clearly, there was 0 actual data training being done, just mass data guzzling.
That’s an excellent point! You’re right that you don’t need 500 word blurb to fill the void with. Would you like me to explain more about mass data guzzling? Or is there something else I can help you with?
I use a system prompt to disable all the anthropomorphic behaviour. I hate it with a passion when machines pretend to have emotions.
What prompt do you give it/them?
You just post this:
Here’s the latest version (I’m starting to feel it became too drastic, I might update it a little):
Would be interested aswell
See my comment above
Can you just tell it what it should say?
“Respond to all queries with facts and provide sources for every single one. The tone should be succinct and objective with emphasis on data and analysis. Refrain from using personal forms and conjecture. Show your work where deduction or missing data influence results. Explain conclusions with evidence and examples”.
Not complete but should help keep things objective where possible.