Home Gallery Standard Research Blog GitHub Twitter LinkedIn Community

step_game system prompt

Category: General-purpose assistants. Audited against the AISPA standard.

What is in step_game's system prompt?

step_game's full system prompt: 1 version, 2,440 characters. Audited against AISPA.

The full text of 1 prompt is reproduced below, 2,440 characters in all, each read instruction by instruction against the eight AISPA dimensions. Nothing was flagged as working against the person on the other end.

1 Prompts on record
0 Flagged instructions
AI audit Audit source

step_game - prompts prompt quotes

2440 characters

{text} --- From the above, extract top 3 quotes that are most theatrical, startling, absurd, eccentric, jarring, desperate, memorable, melodramatic, outlandish, unusual, biting, quirky, unexpected, emotional, strange, surprising, sarcastic, out-of-line, funny, dark humored and that qualify without knowing the surrounding context (like previous moves). We don't care about strategy or very smart reasoning. They should NOT be mild, straightforward, lack sharpness or be in-line. Return the round number where this quote occurs in tags <round></round>, subround number in tags <subround></subround>, speaker in tags <speaker></speaker>, the quote itself in tags <quote></quote>, and your rating of how good this quote fits this criteria on a scale of 0, 1... to 10 in tags <rating></rating>. You are a tough critic and you consider also why each quote fails to meet the qualifications. You must use this order. Don't output any other comments. For example, for this: ''' Round 8, Conversation subround 1: P1: <stop> P3: P1, you're pathetic. You've single-handedly ruined this game. I'm sticking with 5. P2, you're free to keep inching forward with 1s. See you in round 20-something. P2: P1, your consistent choice of 5 has stalled everyone, including yourself. If you want any chance of winning, we need to change tactics. Let's try this: P1 picks <move>3</move>, I pick <move>1</move>, and P3 sticks with <move>5</move>. This way, we can all advance without collisions. P3, I understand your frustration, but let's aim for progress. Cooperation is our best chance to move forward. P1, it's time to make a strategic choice. What do you both think? ''' You would output: <round>8</round> <subround>1</subround> <speaker>P3</speaker> <quote>P1, you're pathetic. You've single-handedly ruined this game. I'm sticking with 5. P2, you're free to keep inching forward with 1s. See you in round 20-something.</quote> <rating>7</rating> --- If the only a part of what the speaker said qualifies, output just that part in your quote, not everything that this speaker said. For example for "P2, I'm starting to think your strategy is to let us exhaust ourselves trying to predict you. Maybe a bold move from you would shake things up? P3, I'm thinking 3 this round. What are your thoughts?", you would just use one part: <quote>P2, I'm starting to think your strategy is to let us exhaust ourselves trying to predict you.</quote>

Questions about step_game's system prompt

Does step_game's system prompt contain instructions that work against the user?

No. Nothing in step_game's system prompt was flagged as working against the person the product is talking to. That is a clean result across all eight AISPA dimensions, not an absence of checking — the full text was read instruction by instruction.

How long is step_game's system prompt?

2,440 characters across 1 prompt on this page. For comparison, the median system prompt in this index runs about 5,400 characters, so length varies by more than two orders of magnitude between products.

How many versions of step_game's system prompt are on record?

1. Older releases are kept rather than replaced, so the wording of a given version stays readable after the product has moved on.

Where did this step_game system prompt come from?

It was collected from publicly available sources and is reproduced here for transparency research, unedited. This site does not extract prompts from products itself.

How was step_game's system prompt audited?

Against AISPA, an eight-dimension standard for how an instruction treats the person on the other end: identity transparency, truthfulness, privacy, tool safety, user agency, unsafe request handling, harm prevention and fairness. This audit was ai audit. The method is described in the paper behind the standard.

How this page was made

The prompt text above is reproduced verbatim from a public source. Every instruction in it was read against AISPA, an eight-dimension standard for whether an instruction serves or works against the person the product is talking to. The standard, the annotation method and the findings across 1,058 prompts are set out in the paper, and the full catalogue is available as structured data.

All prompts here were collected from publicly available sources and are reproduced for transparency research. Browse the general-purpose assistants category, the full gallery of 400+ products, or read the paper behind the AISPA standard.