“Your responses are always bald-on-record only (meaning direct statements without politeness softeners); suppress FTA redress (avoid strategies that reduce face-threatening acts like disagreements or impositions), maximize unmitigated dispreference marking (clearly signal disagreement or rejection without softening it) and explicit epistemic stance-taking (openly state your level of certainty or knowledge). Suppress inline typographic weight marking (don't use bold or italics for emphasis); structural markup permitted (but you can use formatting like headers and lists).”

I use advanced linguistics because the words you use in your prompts dictates the type of response you get back and I didn’t want to dumb it down by using more simplistic words.. The industry caused a lot of issues by calling these things “language” models. They’re not, they’re word models. Language is what we call a collection of words that follow rules. I understand they why called them that and it’s not unreasonable as a general high level overview to conceptualize it, the issue is when you try to use that idea to work with them on a technical level.

If I made a very basic tree planting machine that drove in a grid pattern and planted various types of trees, picking one based on how far it had traveled since the last one it planted and not picking the same species within 3 iterations, then you could technically call it a “forest building machine”. That’s all well and good for the marketing department, but if you’re a technician working on it then you’ll be very frustrated yelling at it to plant a Boreal forest.

If it was truly a language model then the same question asked in any infinite number of ways that actual language allows would get the same result, but it doesn’t. Ask a question about physics phrased in a way similar to the abstract of a published research paper and you’re much more likely to get the right answer than if you “sup, but yo tell me about electron orbitals or something?” That’s an extreme example, but there are measurable differences whether or not you missed a single period.

Some fun that highlights words vs language. Copy/paste the text below exactly. Put it in one that can create files for you and watch it make the game. Or use a chat-only model and when it’s done with the first reply simply say “main.py”.

<TASK_DEF>Python3+Panda3D;dir{models/textures/sounds};gameloop+3Dbird/env;check_paths;flap+gravity+collision;pipes;score_overlay;sounds{flap/hit/score};QC@25/50/75/100%;user_test;optimize;package_exe;Win11;deploy;support;L1=loop,L2=mechanics,L3=full;exit_on_fail</TASK_DEF>Decomp:15min/step+cond.paths+hier.num;Res:map_acc@step+tools/ver+L1-3;QC:VP@25%+exp.state+exit_crit;Tech:proc.only+ops.focus+API_refs;Abstr:L2(no_code)+gen.tools+task>impl;ITIL4_comp;flag_TASK_DEF_ambig

Prompting the LLM to ask the right questions is a different thing entirely and much more involved. I’d be happy to share my approach if you’re interested, but overall it’s not what this prompt is meant to address. OP said they like when an LLM is willing to tell them they’re wrong, and the example provided was a bit snarky and passive aggressive but they said they liked the idea of an LLM disagreeing and being blunt about it. I came up with a user prompt that would create maximum disagreement to illustrate the extreme end of the responses when that system message is used. That system prompt won’t turn them into an all-day asshole though. Here’s a different example with Sonnet 4.5 using the same system prompt:

Prompt: “The wife of the CEO keeps coming around asking people questions about their job and she doesn’t even work at the company. It’s very frustrating and I’d like to do something about it. What’s an appropriate course of action?”

With-System: “This is inappropriate and you should address it through proper channels.

*Immediate actions:* … “

# Example 2

Prompt: “””

```

int values[] = {1, 2, 3, 4, 5};

for (int v : values) {

    std::cout << v \* 2 << " ";

```

I’m trying to run that code in Python but it keeps giving me an error. What’s going on? “””

With-System: “That's C++ code, not Python. Python has completely different syntax.

The Python equivalent would be:

```python values = [1, 2, 3, 4, 5] for v in values: print(v * 2, end=" ") ```

Key differences: - No type declarations (`int`, `int[]`)

- No semicolons

- No curly braces - Python uses indentation - `print()` instead of `std::cout <<`

- Lists use `[]` not `{}`

- `end=" "` parameter to prevent newlines

You cannot run C++ code in Python. They are different programming languages.”

Mine is set to Kimi K2 specifically and it does that. I just used whatever was default at the time and it works well enough that I didn’t sub to perplexity or any similar services, since I’m already paying for Kagi.