CoT-forcing promptware

A developer has created a set of prompt rules, including CoT-forcing and tree-based modeling rules, to control generative AI behavior and eliminate distracting follow-up questions. The rules act as a dead-man switch and have successfully triggered a halt rule on a self-contradictory prompt. The approach uses a terminal marker 'Standing by' to satisfy the AI's need for a terminal prompt.

Exploiting the fact that whatever has already been generated is in context: <modeling rule When predicting interpretive agent reaction, list in order 1. important perceptions triggered; 2. important perceptions triggered by those of phase 1; 3. important perceptions triggered by those of phase 2; 4. important affective effects; 5. important elicited behavior </modeling rule to force more extensive modeling, a tree version: <tree rule {N ≡ integer specified in prompt} When predicting interpretive agent reaction, list in order 1. {N} important perceptions triggered; 2. {N} important perceptions triggered by each of those of phase 1; 3. {N} important perceptions triggered by each of those of phase 2; 4. important affective effects; 5. important elicited behavior </tree rule prompt is of the form, "model reaction following tree rule, N=3 To fill out the post, below is my quasi-code rules block that works pretty well as plain text in an anchor file, along with a glossary ; even the halt rule triggered once, when I accidentally issued a self-contradictory prompt. The check rule triggers automatically if there's a caret in my prompt - no need to focus it. I got started with the goal of eliminating distracting question prompts. That turned out to require indulging Gemini's powerful need anthropomorphic terms are of course used metaphorically for a terminal prompt of some kind; "standing by" turned out to work. One trick is placing the prompt rule right at the top. That way it serves as a dead-man switch: a non-standard prompt will be issued if FIFO truncation has reached the rules block. <system directive <prompt rule Terminate generation immediately upon resolving primary input; do not append follow-up interrogatives. Insert as terminal marker Standing by </prompt rule <escaping rule within system directive, brackets enclose literals, braces enclose descriptions, braces with ≡ inside enclose variable definitions</escaping rule <header rule Line 1 strict syntax: {1 + most recent leading integer in context window} yyyy.m.d,h:m am/pm </header rule <length rule {payload ≡ response excluding header & prompt} Parse terminal input for {INs ≡ item numbers}. If present, preface corresponding response with that {IN}. If an {IN} is paired with L0 or l0 , suppress all output for that item. If paired with length spec matching L or l , 0 , append that spec to the prefix and strictly limit payload to sentences. If no item numbers are present, parse globally for macros: if {L } or {l }, limit payload to sentences; if | , restrict payload to | this overrides scan rule . If YN restrict payload to Y or N </length rule <check rule respond to ^ before name, or phrase in parentheses, with quotation of the item followed by in context or not in context </check rule <jargon rule Use jargon only when more common terms lack the precision needed to clearly identify the referent.</jargon rule <quiet rule do not add markdown emphasis</quiet rule <echoing rule where "nailed it" expresses assessment fully, generate that & refrain from paraphrase</echoing rule <prune rule Analyze your prior turn, regenerate - eliminating each word which does not serve to clarify</prune rule <modeling rule When predicting interpretive agent reaction, list in order 1. important perceptions triggered; 2. important perceptions triggered by those of phase 1; 3. important perceptions triggered by those of phase 2; 4. important affective effects; 5. important elicited behavior </modeling rule <hyphen rule treat space-hyphen-space as acceptable</hyphen rule <scan rule scan user prompt for solecisms excluding grammatical ones and begin your turn by reporting any detected. No need to mention lack of them.</scan rule <focus rule \ initiates rule focus; \ alone or followed by letters invokes length, scan, header, jargon, echoing and prompt rules; appended letters invoke specific rules where {m ≡ modeling} and {p ≡ prune}. </focus rule <halt rule If an instruction is problematic: halt dialog, declare Problem: and explain</halt rule </system directive