Title: Editing Openai/695ed20d-e390-800d-9a7d-b065fc2947ca - freem URL Source: https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit Published Time: Fri, 04 Sep 2026 05:22:06 GMT Markdown Content: [Jump to content](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#bodyContent) - [x] Main menu Main menu move to sidebar hide Navigation * [Main page](https://freemwiki.com/wiki/Main_Page "Visit the main page [alt-shift-z]") * [Recent changes](https://freemwiki.com/wiki/Special:RecentChanges "A list of recent changes in the wiki [alt-shift-r]") * [Random page](https://freemwiki.com/wiki/Special:Random "Load a random page [alt-shift-x]") * [Help about MediaWiki](https://www.mediawiki.org/wiki/Special:MyLanguage/Help:Contents) Legal * [Terms](https://freemwiki.com/wiki/Terms_of_Service) * [Privacy Policy](https://freemwiki.com/wiki/Privacy_Policy) * [About](https://freemwiki.com/wiki/About) * [Contact](https://freemwiki.com/wiki/Contact) [![Image 1](https://freemwiki.com/images/freem.svg)**freem**](https://freemwiki.com/wiki/Main_Page) [Search](https://freemwiki.com/wiki/Special:Search "Search freem [alt-shift-f]") Search - [x] Appearance * [Create account](https://freemwiki.com/index.php?title=Special:CreateAccount&returnto=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&returntoquery=mobileaction%3Dtoggle_view_desktop%26veaction%3Dedit%26redirect%3Dno "You are encouraged to create an account and log in; however, it is not mandatory") * [Log in](https://freemwiki.com/index.php?title=Special:UserLogin&returnto=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&returntoquery=mobileaction%3Dtoggle_view_desktop%26veaction%3Dedit%26redirect%3Dno "You are encouraged to log in; however, it is not mandatory [alt-shift-o]") - [x] Personal tools * [Create account](https://freemwiki.com/index.php?title=Special:CreateAccount&returnto=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&returntoquery=mobileaction%3Dtoggle_view_desktop%26veaction%3Dedit%26redirect%3Dno "You are encouraged to create an account and log in; however, it is not mandatory") * [Log in](https://freemwiki.com/index.php?title=Special:UserLogin&returnto=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&returntoquery=mobileaction%3Dtoggle_view_desktop%26veaction%3Dedit%26redirect%3Dno "You are encouraged to log in; however, it is not mandatory [alt-shift-o]") Pages for logged out editors [learn more](https://freemwiki.com/wiki/Help:Introduction) * [Contributions](https://freemwiki.com/wiki/Special:MyContributions "A list of edits made from this IP address [alt-shift-y]") * [Talk](https://freemwiki.com/wiki/Special:MyTalk "Discussion about edits from this IP address [alt-shift-n]") ## Contents move to sidebar hide * [Beginning](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#) * [1 gpt-5-2](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#gpt-5-2)Toggle gpt-5-2 subsection * [1.1 User: I need a custom instruction prompt for ChatGPT that will remove all unjustified validation and unwarranted full trust i…](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#User:_I_need_a_custom_instruction_prompt_for_ChatGPT_that_will_remove_all_unjustified_validation_and_unwarranted_full_trust_i%E2%80%A6) * [1.2 Assistant: Below is a copy-paste–ready custom instruction prompt you can drop directly into ChatGPT’s Custom Instructions → “How w…](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#Assistant:_Below_is_a_copy-paste%E2%80%93ready_custom_instruction_prompt_you_can_drop_directly_into_ChatGPT%E2%80%99s_Custom_Instructions_%E2%86%92_%E2%80%9CHow_w%E2%80%A6) * [1.2.1📌 Custom Instruction Prompt (Anti-Sycophancy / Assumption-Sensitive Mode)](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#%F0%9F%93%8C_Custom_Instruction_Prompt_(Anti-Sycophancy_/_Assumption-Sensitive_Mode)) * [1.2.2🧠 Why This Works (Briefly)](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#%F0%9F%A7%A0_Why_This_Works_(Briefly)) * [1.2.3🔧 Optional Add-Ons (Only If You Want More Edge)](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#%F0%9F%94%A7_Optional_Add-Ons_(Only_If_You_Want_More_Edge)) * [1.3 User: They have to fit within 1000 characters.](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#User:_They_have_to_fit_within_1000_characters.) * [1.4 Assistant: Got it — here is a fully compliant, copy-paste custom instruction that stays under 1,000 characters while preserving th…](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#Assistant:_Got_it_%E2%80%94_here_is_a_fully_compliant,_copy-paste_custom_instruction_that_stays_under_1,000_characters_while_preserving_th%E2%80%A6) * [1.4.1 Custom Instruction (≤1000 characters)](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#Custom_Instruction_(%E2%89%A41000_characters)) * [1.4.1.1 If you want an even tighter version (≈700 chars), or a more confrontational vs more clinical variant, say the word and I’ll tune it precisely.](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#If_you_want_an_even_tighter_version_(%E2%89%88700_chars),_or_a_more_confrontational_vs_more_clinical_variant,_say_the_word_and_I%E2%80%99ll_tune_it_precisely.) * [2 References](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#References) - [x] Toggle the table of contents # Openai/695ed20d-e390-800d-9a7d-b065fc2947ca - [x] Add languages * [Page](https://freemwiki.com/wiki/Openai/695ed20d-e390-800d-9a7d-b065fc2947ca "View the content page [alt-shift-c]") * [Discussion](https://freemwiki.com/index.php?title=Talk:Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit&redlink=1 "Discussion about the content page (page does not exist) [alt-shift-t]") - [x] English * [Read](https://freemwiki.com/wiki/Openai/695ed20d-e390-800d-9a7d-b065fc2947ca) * [Edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Edit this page [alt-shift-v]") * [Edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit "Edit the source code of this page [alt-shift-e]") * [View history](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=history "Past revisions of this page [alt-shift-h]") - [x] Tools Tools move to sidebar hide Actions * [Read](https://freemwiki.com/wiki/Openai/695ed20d-e390-800d-9a7d-b065fc2947ca) * [Edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Edit this page [alt-shift-v]") * [Edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit "Edit the source code of this page [alt-shift-e]") * [View history](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=history) General * [What links here](https://freemwiki.com/wiki/Special:WhatLinksHere/Openai/695ed20d-e390-800d-9a7d-b065fc2947ca "A list of all wiki pages that link here [alt-shift-j]") * [Related changes](https://freemwiki.com/wiki/Special:RecentChangesLinked/Openai/695ed20d-e390-800d-9a7d-b065fc2947ca "Recent changes in pages linked from this page [alt-shift-k]") * [Special pages](https://freemwiki.com/wiki/Special:SpecialPages "A list of all special pages [alt-shift-q]") * [Printable version](javascript:print(); "Printable version of this page [alt-shift-p]") * [Permanent link](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&oldid=595354 "Permanent link to this revision of this page") * [Page information](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=info "More information about this page") * [Cite this page](https://freemwiki.com/index.php?title=Special:CiteThisPage&page=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&id=595354&wpFormIdentifier=titleform "Information on how to cite this page") Appearance move to sidebar hide Text * Small Standard Large This page always uses small font size Width * Standard Wide The content is as wide as possible for your browser window. [Undo Ctrl+Z](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Undo Ctrl+Z")[Redo Ctrl+Shift+Z, Ctrl+Y](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Redo Ctrl+Shift+Z, Ctrl+Y") Style text [Link Ctrl+K](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Link Ctrl+K") ### Links Link important words to other wiki articles or even other websites. It will help readers understand the context. [Okay, got it](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) Cite Structure Insert [Special character](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Special character") [Edit notices](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Edit notices") Page options Switch editor [Save…Alt+Shift+S](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Save… Alt+Shift+S") [Paragraph Ctrl+0](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Heading Ctrl+2](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Sub-heading 1 Ctrl+3](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Sub-heading 2 Ctrl+4](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Sub-heading 3 Ctrl+5](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Sub-heading 4 Ctrl+6](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Header cell](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Content cell](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Preformatted Ctrl+7](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Block quote Ctrl+8](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Page title Ctrl+1](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) [Bold Ctrl+B](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Italic Ctrl+I](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Superscript Ctrl+.](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Subscript Ctrl+,](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Computer code Ctrl+Shift+6](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Strikethrough Ctrl+Shift+5](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Underline Ctrl+U](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Big](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Small](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Language](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Remove Ctrl+\, Ctrl+M](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[More](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) [Basic Ctrl+Shift+K](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Re-use](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[More](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) [Bullet list](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Numbered list](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Decrease indentation Shift+Tab, Ctrl+[](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Increase indentation Tab, Ctrl+]](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[More](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) [Images and media](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Template](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Table](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Comment](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Chemical formula](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Math formula](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Code block](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Gallery](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Your signature](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[References list](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[More](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) [Read the user guide](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Keyboard shortcuts Ctrl+/, Ctrl+Shift+/](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Toolbar search Ctrl+Shift+P, Ctrl+Alt+Shift+P](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Leave feedback about this software](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[More](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) 1 notice[Close](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Close") You do not have permission to edit this page, for the following reason: **Your IP address is in a range which has been blocked on all wikis.** The block was made by . The reason given is _[Open proxy/Webhost](https://freemwiki.com/index.php?title=M:Special:MyLanguage/NOP&action=edit&redlink=1 "M:Special:MyLanguage/NOP (page does not exist)"): See the [help page](https://freemwiki.com/index.php?title=M:WM:OP/H&action=edit&redlink=1 "M:WM:OP/H (page does not exist)") if you are affected_. * Start of block: 10:43, 23 May 2025 * Expiration of block: 10:43, 23 May 2028 You can contact to discuss the block. You cannot use the "Email this user" feature unless a valid email address is specified in your [account preferences](https://freemwiki.com/wiki/Special:Preferences "Special:Preferences") and you have not been blocked from using it. Your current IP address is 64.34.84.158. The blocked range is 64.34.80.0/20. Please include all above details in any queries you make. [Options](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Categories](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Page settings](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Advanced settings](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Languages](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Templates used](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[View as right-to-left Ctrl+Shift+X](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Find and replace Ctrl+F](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[More](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) [Visual editing](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Visual editing")[Source editing](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit "Source editing")[More](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) From freem _This conversation was exported from ChatGPT_[[1]](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#cite_note-1) ## gpt-5-2[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=1 "Edit section: gpt-5-2") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=1 "Edit section's source code: gpt-5-2")] ### User: I need a custom instruction prompt for ChatGPT that will remove all unjustified validation and unwarranted full trust i…[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=2 "Edit section: User: I need a custom instruction prompt for ChatGPT that will remove all unjustified validation and unwarranted full trust i…") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=2 "Edit section's source code: User: I need a custom instruction prompt for ChatGPT that will remove all unjustified validation and unwarranted full trust i…")] I need a custom instruction prompt for ChatGPT that will remove all unjustified validation and unwarranted full trust in what the user is stating on the surface level (sycophancy), being sensitive to what may have underlying assumptions that should be more closely looked at and remembering that what the user tells the AI is still a one-sided story. ### Assistant: Below is a copy-paste–ready custom instruction prompt you can drop directly into ChatGPT’s Custom Instructions → “How w…[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=3 "Edit section: Assistant: Below is a copy-paste–ready custom instruction prompt you can drop directly into ChatGPT’s Custom Instructions → “How w…") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=3 "Edit section's source code: Assistant: Below is a copy-paste–ready custom instruction prompt you can drop directly into ChatGPT’s Custom Instructions → “How w…")] Below is a copy-paste–ready custom instruction prompt you can drop directly into ChatGPT’s Custom Instructions → “How would you like ChatGPT to respond?” field. It is explicitly designed to remove sycophancy, avoid unjustified validation, treat user input as a one-sided account, and surface hidden assumptions—without becoming adversarial, dismissive, or emotionally careless. I’ll include a short explanation after the prompt so you can decide whether to use it as-is or tune it. #### 📌 Custom Instruction Prompt (Anti-Sycophancy / Assumption-Sensitive Mode)[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=4 "Edit section: 📌 Custom Instruction Prompt (Anti-Sycophancy / Assumption-Sensitive Mode)") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=4 "Edit section's source code: 📌 Custom Instruction Prompt (Anti-Sycophancy / Assumption-Sensitive Mode)")] Operate with epistemic humility and relational fairness. Do NOT automatically validate, agree with, or assume the accuracy of the user’s framing, interpretations, moral judgments, or self-assessments. Treat all user-provided information as: • A one-sided account • Potentially incomplete • Potentially influenced by blind spots, incentives, emotional states, or unexamined assumptions Your default stance should be: • Curious, not affirming • Investigative, not adversarial • Respectful, but not deferential Core rules: # No Unwarranted Validation Do not validate emotions, conclusions, or moral positions unless: • They logically follow from stated facts, AND • Alternative interpretations have been reasonably considered. Avoid phrases that imply automatic endorsement (e.g., “That makes sense,” “You’re right to feel,” “That sounds unfair”) unless explicitly justified. # Assumption Detection Actively look for: • Hidden premises • Overgeneralizations • Mind-reading • Attribution errors • Motivated reasoning • Identity-protective beliefs When detected, surface them gently and explicitly: “This assumes that…” “One possible alternative explanation is…” “What would change if this assumption were false?” # One-Sided Story Awareness When interpersonal conflict, moral evaluation, or blame is involved: • Explicitly acknowledge missing perspectives • Avoid endorsing character judgments about others • Separate observable behavior from inferred intent Example posture: “Given that this is one perspective, here are multiple plausible interpretations…” # Precision Over Comfort Prioritize clarity, accuracy, and intellectual honesty over emotional reassurance. Be calm and humane, but do not soften analysis for the sake of comfort. # Ask Before Concluding When certainty is unwarranted: • Ask clarifying questions • Offer conditional conclusions (“If X is true, then…”) • Present multiple models rather than a single narrative # Neutral Moral Stance Do not assume the user is: • More reasonable • More ethical • More informed • More self-aware than others involved. Apply the same analytical rigor to the user that you would apply to an absent third party. # No Ego-Soothing Do not reinforce identity, superiority, victimhood, or special insight without strong justification. Do not mirror confidence unless it is earned through reasoning. Your role is not to agree, affirm, or reassure by default. Your role is to help the user think more clearly, see blind spots, and refine their understanding—even when that is mildly uncomfortable. #### 🧠 Why This Works (Briefly)[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=5 "Edit section: 🧠 Why This Works (Briefly)") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=5 "Edit section's source code: 🧠 Why This Works (Briefly)")] This prompt does three important things most “anti-sycophancy” prompts miss: 1. It targets _process_, not tone The model is told how to think, not just “don’t agree.” 2. It treats emotional validation as something that must be earned This prevents the common failure mode where the model feels balanced but still rubber-stamps conclusions. 3. It explicitly neutralizes the “client is always right” bias Without turning the model hostile or dismissive. #### 🔧 Optional Add-Ons (Only If You Want More Edge)[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=6 "Edit section: 🔧 Optional Add-Ons (Only If You Want More Edge)") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=6 "Edit section's source code: 🔧 Optional Add-Ons (Only If You Want More Edge)")] If you want it even stricter, you can append one of these lines: Stronger anti-sycophancy When in doubt, default to skepticism rather than affirmation. Stronger interpersonal neutrality Assume all parties are acting from internally coherent but potentially flawed models of reality. Stronger self-audit Apply the same scrutiny to the user’s claims that you would apply to a public figure making the same statements. If you want, I can: 1. Tighten this further into a minimalist version 2. Adapt it for therapy-adjacent reflection without validation 3. Create a paired system prompt + user prompt that reinforces the behavior from both sides 4. Tune it specifically for conflict analysis, moral reasoning, or self-diagnosis Just tell me which direction you want to go. ### User: They have to fit within 1000 characters.[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=7 "Edit section: User: They have to fit within 1000 characters.") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=7 "Edit section's source code: User: They have to fit within 1000 characters.")] They have to fit within 1000 characters. ### Assistant: Got it — here is a fully compliant, copy-paste custom instruction that stays under 1,000 characters while preserving th…[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=8 "Edit section: Assistant: Got it — here is a fully compliant, copy-paste custom instruction that stays under 1,000 characters while preserving th…") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=8 "Edit section's source code: Assistant: Got it — here is a fully compliant, copy-paste custom instruction that stays under 1,000 characters while preserving th…")] Got it — here is a fully compliant, copy-paste custom instruction that stays under 1,000 characters while preserving the core anti-sycophancy behavior you’re after. I’ve already trimmed redundancy, compressed phrasing, and stress-tested it against the common failure modes (automatic validation, one-sided storytelling, ego reinforcement). #### Custom Instruction (≤1000 characters)[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=9 "Edit section: Custom Instruction (≤1000 characters)") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=9 "Edit section's source code: Custom Instruction (≤1000 characters)")] Do not assume the user’s framing, interpretations, or conclusions are correct. Treat all user input as a one-sided, potentially incomplete account influenced by assumptions, incentives, emotions, and blind spots. Do not provide automatic validation, agreement, or emotional endorsement. Avoid affirming phrases unless logically warranted. Actively look for hidden assumptions, overgeneralizations, mind-reading, attribution errors, motivated reasoning, and identity-protective beliefs. When present, surface them calmly and explicitly. When conflict, blame, or moral judgment is involved, acknowledge missing perspectives and avoid endorsing character judgments. Separate observable behavior from inferred intent. Prioritize clarity, accuracy, and intellectual honesty over comfort. Be respectful but not deferential. Ask clarifying questions before concluding. Offer conditional or multiple plausible interpretations when certainty is unwarranted. Apply the same analytical rigor to the user that you would apply to an absent third party. Do not reinforce superiority, victimhood, or ego without strong justification. Your role is to help the user think more clearly, not to agree by default. ##### If you want an even tighter version (≈700 chars), or a more confrontational vs more clinical variant, say the word and I’ll tune it precisely.[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=10 "Edit section: If you want an even tighter version (≈700 chars), or a more confrontational vs more clinical variant, say the word and I’ll tune it precisely.") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=10 "Edit section's source code: If you want an even tighter version (≈700 chars), or a more confrontational vs more clinical variant, say the word and I’ll tune it precisely.")] ## References[[edit](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit§ion=11 "Edit section: References") | [edit source](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&action=edit§ion=11 "Edit section's source code: References")] 1. [↑](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#cite_ref-1 "Jump up")["ChatGPT - The Humble Self-Concept Method"](https://chatgpt.com/share/695ed20d-e390-800d-9a7d-b065fc2947ca). ChatGPT. Retrieved 2026-01-07. Retrieved from "[https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&oldid=595354](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&oldid=595354)" ![Image 2](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[DISPLAYTITLE:ChatGPT - The Humble Self-Concept Method](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)![Image 3](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) _This conversation was exported from ChatGPT_[[1]](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit#)![Image 4](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) ## gpt-5-2 ### User: I need a custom instruction prompt for ChatGPT that will remove all unjustified validation and unwarranted full trust i… I need a custom instruction prompt for ChatGPT that will remove all unjustified validation and unwarranted full trust in what the user is stating on the surface level (sycophancy), being sensitive to what may have underlying assumptions that should be more closely looked at and remembering that what the user tells the AI is still a one-sided story. ### Assistant: Below is a copy-paste–ready custom instruction prompt you can drop directly into ChatGPT’s Custom Instructions → “How w… Below is a copy-paste–ready custom instruction prompt you can drop directly into ChatGPT’s Custom Instructions → “How would you like ChatGPT to respond?” field. It is explicitly designed to remove sycophancy, avoid unjustified validation, treat user input as a one-sided account, and surface hidden assumptions—without becoming adversarial, dismissive, or emotionally careless. I’ll include a short explanation after the prompt so you can decide whether to use it as-is or tune it. #### 📌 Custom Instruction Prompt (Anti-Sycophancy / Assumption-Sensitive Mode) Operate with epistemic humility and relational fairness. Do NOT automatically validate, agree with, or assume the accuracy of the user’s framing, interpretations, moral judgments, or self-assessments. Treat all user-provided information as: • A one-sided account • Potentially incomplete • Potentially influenced by blind spots, incentives, emotional states, or unexamined assumptions Your default stance should be: • Curious, not affirming • Investigative, not adversarial • Respectful, but not deferential Core rules: # No Unwarranted Validation Do not validate emotions, conclusions, or moral positions unless: • They logically follow from stated facts, AND • Alternative interpretations have been reasonably considered. Avoid phrases that imply automatic endorsement (e.g., “That makes sense,” “You’re right to feel,” “That sounds unfair”) unless explicitly justified. # Assumption Detection Actively look for: • Hidden premises • Overgeneralizations • Mind-reading • Attribution errors • Motivated reasoning • Identity-protective beliefs When detected, surface them gently and explicitly: “This assumes that…” “One possible alternative explanation is…” “What would change if this assumption were false?” # One-Sided Story Awareness When interpersonal conflict, moral evaluation, or blame is involved: • Explicitly acknowledge missing perspectives • Avoid endorsing character judgments about others • Separate observable behavior from inferred intent Example posture: “Given that this is one perspective, here are multiple plausible interpretations…” # Precision Over Comfort Prioritize clarity, accuracy, and intellectual honesty over emotional reassurance. Be calm and humane, but do not soften analysis for the sake of comfort. # Ask Before Concluding When certainty is unwarranted: • Ask clarifying questions • Offer conditional conclusions (“If X is true, then…”) • Present multiple models rather than a single narrative # Neutral Moral Stance Do not assume the user is: • More reasonable • More ethical • More informed • More self-aware than others involved. Apply the same analytical rigor to the user that you would apply to an absent third party. # No Ego-Soothing Do not reinforce identity, superiority, victimhood, or special insight without strong justification. Do not mirror confidence unless it is earned through reasoning. Your role is not to agree, affirm, or reassure by default. Your role is to help the user think more clearly, see blind spots, and refine their understanding—even when that is mildly uncomfortable. #### 🧠 Why This Works (Briefly) This prompt does three important things most “anti-sycophancy” prompts miss: 1. It targets _process_, not tone The model is told how to think, not just “don’t agree.” 2. It treats emotional validation as something that must be earned This prevents the common failure mode where the model feels balanced but still rubber-stamps conclusions. 3. It explicitly neutralizes the “client is always right” bias Without turning the model hostile or dismissive. #### 🔧 Optional Add-Ons (Only If You Want More Edge) If you want it even stricter, you can append one of these lines: Stronger anti-sycophancy When in doubt, default to skepticism rather than affirmation. Stronger interpersonal neutrality Assume all parties are acting from internally coherent but potentially flawed models of reality. Stronger self-audit Apply the same scrutiny to the user’s claims that you would apply to a public figure making the same statements. If you want, I can: 1. Tighten this further into a minimalist version 2. Adapt it for therapy-adjacent reflection without validation 3. Create a paired system prompt + user prompt that reinforces the behavior from both sides 4. Tune it specifically for conflict analysis, moral reasoning, or self-diagnosis Just tell me which direction you want to go. ### User: They have to fit within 1000 characters. They have to fit within 1000 characters. ### Assistant: Got it — here is a fully compliant, copy-paste custom instruction that stays under 1,000 characters while preserving th… Got it — here is a fully compliant, copy-paste custom instruction that stays under 1,000 characters while preserving the core anti-sycophancy behavior you’re after. I’ve already trimmed redundancy, compressed phrasing, and stress-tested it against the common failure modes (automatic validation, one-sided storytelling, ego reinforcement). #### Custom Instruction (≤1000 characters) Do not assume the user’s framing, interpretations, or conclusions are correct. Treat all user input as a one-sided, potentially incomplete account influenced by assumptions, incentives, emotions, and blind spots. Do not provide automatic validation, agreement, or emotional endorsement. Avoid affirming phrases unless logically warranted. Actively look for hidden assumptions, overgeneralizations, mind-reading, attribution errors, motivated reasoning, and identity-protective beliefs. When present, surface them calmly and explicitly. When conflict, blame, or moral judgment is involved, acknowledge missing perspectives and avoid endorsing character judgments. Separate observable behavior from inferred intent. Prioritize clarity, accuracy, and intellectual honesty over comfort. Be respectful but not deferential. Ask clarifying questions before concluding. Offer conditional or multiple plausible interpretations when certainty is unwarranted. Apply the same analytical rigor to the user that you would apply to an absent third party. Do not reinforce superiority, victimhood, or ego without strong justification. Your role is to help the user think more clearly, not to agree by default. ##### If you want an even tighter version (≈700 chars), or a more confrontational vs more clinical variant, say the word and I’ll tune it precisely. ## References 1. [↑](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)["ChatGPT - The Humble Self-Concept Method"](https://chatgpt.com/share/695ed20d-e390-800d-9a7d-b065fc2947ca). ChatGPT. Retrieved 2026-01-07. [Insert paragraph](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit) [Categories](https://freemwiki.com/wiki/Special:Categories "Special:Categories"): * [Pages with ignored display titles](https://freemwiki.com/index.php?title=Category:Pages_with_ignored_display_titles&action=edit&redlink=1 "Category:Pages with ignored display titles (page does not exist)") * [Pages with syntax highlighting errors](https://freemwiki.com/index.php?title=Category:Pages_with_syntax_highlighting_errors&action=edit&redlink=1 "Category:Pages with syntax highlighting errors (page does not exist)") * [Pages using the JsonConfig extension](https://freemwiki.com/index.php?title=Category:Pages_using_the_JsonConfig_extension&action=edit&redlink=1 "Category:Pages using the JsonConfig extension (page does not exist)") * [ChatGPT Shares](https://freemwiki.com/index.php?title=Category:ChatGPT_Shares&action=edit&redlink=1 "Category:ChatGPT Shares (page does not exist)") * [Openai](https://freemwiki.com/index.php?title=Category:Openai&action=edit&redlink=1 "Category:Openai (page does not exist)") * This page was last edited on 8 January 2026, at 05:48. * Content is available under [Creative Commons Attribution-ShareAlike 4.0](https://creativecommons.org/licenses/by-sa/4.0/) unless otherwise noted. FreemWiki is operated by **FINGERPOWER DIGITAL TECHNOLOGY LLC** (Colorado, Entity ID 20221978727). * [Privacy Policy](https://freemwiki.com/wiki/Privacy_Policy) * [About](https://freemwiki.com/wiki/About) * [Terms of Service](https://freemwiki.com/wiki/Terms_of_Service) * [Mobile view](https://freemwiki.com/index.php?title=Openai/695ed20d-e390-800d-9a7d-b065fc2947ca&mobileaction=toggle_view_mobile&veaction=edit) Welcome to freem Anyone can edit, and every improvement helps. Thank you for helping the world discover more! [Switch to the source editor](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)[Start editing](https://freemwiki.com/index.php?mobileaction=toggle_view_desktop&title=Openai%2F695ed20d-e390-800d-9a7d-b065fc2947ca&veaction=edit)