prompt clarity

Compression requires clarity; muddy prompts compress poorly, wasting the model's representational capacity

'questions they ask' and 'vocabulary they use' are direct manifestations of prompt clarity—how well the user articulates the problem in context.

Author explicitly identifies vague questioning (含含糊糊的问一句) as the root cause of AI misuse; this is a failure mode of low prompt clarity.

The prompt 'Please share with me your unique, original reflection on humanity' is exceptionally clear about what problem it's solving (get philosophical insight, not generic output). The quality of re

Before/after examples show direct correlation between prompt clarity (outcome-based vs process-based) and agent behavior.

Natural language constraint ('use gh CLI') outperforms formal tool definitions, suggesting clarity/simplicity in prompting matters more than comprehensiveness.

The insight that 'Market Analyst Agent' outperforms 'Research Agent' is fundamentally about prompt/context clarity—narrow definition reduces ambiguity.

Yang's core insight is that clarity about what AI produces is the limiting factor. This is equivalent to prompt clarity—understanding what the system is doing requires clear mental models of its outpu

The output-first pattern is a specific instantiation of the general principle that AI systems perform better with clear, well-defined inputs. Writing the customer view first IS a prompt clarity techni

Booch's journey demonstrates that clear, simple problem statements (the boring option) outperform complex exploratory prompts. This is about prompt clarity—what you ask the AI matters less than how cl

Author has clear prompts (summaries of fable/sol) but output is still opaque due to model's invented jargon. This shows prompt clarity alone doesn't guarantee output clarity.

The failure directly stems from unclear problem framing. Claude's behavior shift indicates the model is highly sensitive to specificity level in user context.

The 'knowing what you want' principle is the highest-level form of prompt clarity—intent must precede wording.

The emphasis on written task lists and explicit problem definition before agent interaction aligns with prompt clarity as foundational context.

Success depended on clear problem statement ('extract useful ideas') which then revealed simpler solution path

The insight that 'focus creates cleaner contact with actual work' mirrors how clear, narrow prompts outperform vague, broad ones

Agent-based architecture forces clarity about agent responsibilities. Each agent needs a clear role and scope, which is a form of context clarity.

Author emphasizes that describing what you want in plain English enables professional outcomes. Suggests clarity of problem specification directly enables context quality.

The clarity about 'what he's about to say' comes from clear mental models built over time—clarity compounds through repeated, preserved interactions

Author suggests interface affects how clearly humans articulate problems to LLMs, implying clarity is bottleneck

Harford's framing implies LLM plausibility is an inherent trait, but practitioner experience shows that clear problem definition and proper context dramatically improves output quality. The article do

Author's frustration likely stems from unclear problem specification ('here's a task, make code'), but they don't recognize this as a lever for improvement. The complaint suggests they're not applying

Article implies that clear thinking (and thus clear problem articulation) is better than AI-generated outputs. Weakly supports thesis that clarity is bottleneck, but doesn't advance HOW to achieve it.

Tweet suggests estimation failed, which COULD indicate unclear problem specification in the prompt, but tweet doesn't confirm this.