{"slug": "cot-forcing-promptware", "title": "CoT-forcing promptware", "summary": "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.", "body_md": "Exploiting the fact that whatever has already been generated is in context:\n\n<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>\n\nto force more extensive modeling, a tree version:\n\n<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>\n\n(prompt is of the form, \"model reaction following tree_rule, N=3)\n\nTo 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.\n\nThe check rule triggers automatically if there's a caret in my prompt - no need to focus it.\n\nI 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.\n\nOne 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.\n\n```\n**<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>**\n```\n\n", "url": "https://wpnews.pro/news/cot-forcing-promptware", "canonical_source": "https://www.lesswrong.com/posts/bx69HehbzEhh9drWp/cot-forcing-promptware", "published_at": "2026-06-18 19:33:56+00:00", "updated_at": "2026-06-18 20:02:31.587203+00:00", "lang": "en", "topics": ["large-language-models", "generative-ai", "ai-tools"], "entities": ["Gemini"], "alternates": {"html": "https://wpnews.pro/news/cot-forcing-promptware", "markdown": "https://wpnews.pro/news/cot-forcing-promptware.md", "text": "https://wpnews.pro/news/cot-forcing-promptware.txt", "jsonld": "https://wpnews.pro/news/cot-forcing-promptware.jsonld"}}