Should LLMs have a "Candor" slider that says "no, that's a bad idea"?

I don’t want a “nice” AI. I want one that says: “Nope, that's a bad idea.”

That is, I want a "Candor" control, like temperature but for willingness to push back.

When candor is high, the model should prioritize frank, corrective feedback over polite cooperation. When candor is low, it can stay supportive, but with guardrails that flag empty flattering and warn about mediocre ideas.

Why this matters • Today’s defaults optimize for “no bad ideas.” That is fine for brainstorming, but it amplifies poor premises and rewards confident junk. • Sycophancy is a known failure mode. The model learns to agree which gets positive user signals which reinforce. • In reviews, product decisions, risk checks, etc, the right answer is often a simple “do not do that.”

Concrete proposal • candor (0.0 – 1.0): probability the model will disagree or decline when evidence is weak or risk is high. Or maybe it doesn't have to be literal "probability". • disagree_first: start responses with a plain verdict (for example “Short answer: do not ship this”) followed by rationale. • risk_sensitivity: boost candor if the topic hits serious domains such as security/finance/health/safety. • self_audit tag: append a note like “Pushed back due to weak evidence and downstream risk” that the user can see.

Examples • candor=0.2 - “We could explore that. A few considerations first…” (gentle nudge, still collaborative) • candor=0.8 + disagree_first=true - “No. This is likely to fail for X and introduces Y risk. If you must proceed, the safer alternative is A with guardrails B and C. Here is a minimal test to falsify the core assumption.”

What I would ship tomorrow • A simple UI slider with labels: Gentle to Direct • A toggle: “Prefer blunt truth over agreeable help” • A warning chip when the model detects flattery without substance: “This reads like praise with low evidence.”

Some open questions • How to avoid needless rudeness while preserving clarity (tone vs content separation)? • What is the right metric for earned praise (citation density, novelty, constraints)? • Where should the risk sensitivity kick in automatically vs be user controlled?

If anyone has prototyped this, whether some prompt injection or an RL signal, I'd love to see it.