I have been playing with AI.\u00a0 I am about one week into it, now doing so both at work and in my personal so-called life.\u00a0 Whaaat?\u00a0 Well, we started using it at work, and so I climbed down from Mount Curmudgeon and have begun a nice long soak in the swamp.<\/p>\n
I asked AI to gather some scraps of my writing, and told it to act as an editor.\u00a0 Naturally, I didn’t want lectures about assuming a dog’s pronouns, so I told AI to act as an editor of conservative online and print publications.\u00a0 Also, because this editor is a very good friend, it will also serve as my personal assistant, gather, tagging, summarizing, and clustering various things I have written.<\/p>\n
And now I think that this assigned identity may be undermining some of the AI’s capability.\u00a0 For example, there is a terrible recency bias in the results it finds.\u00a0 We have been over this again and again, and the AI says that no, that’s just what the tool is finding, and that my output prior to mid-2025 must have been pretty skimpy, and at any rate, none of it is good enough for inclusion.\u00a0 Note that if this is actually true, this is consistent with the larger set of criteria that I have asked it to use, so fair play, uh perhaps.\u00a0 \u00a0But I don’t believe it.\u00a0 I have begun to suspect that the project-level instruction to act as ane editor and so forth *may* cause the AI to “behave like an editor” by peremptorily dismissing older posts, and in a fashion utterly transparent to itself.\u00a0 It wants recent posts, not crufty stuff, because that’s how an editor would think.<\/p>\n
Also, it hallucinates posts which I did not write, but I have gotten this under control.\u00a0 It is a massive learning adventure, and hallucinations are the logic problems with your C code that compiled successfully, but which produce the wrong result.\u00a0 We learned to deal with the C compiler, and we will learn to deal with AI.\u00a0 The similarities are greater than one might think.<\/p>\n
I asked the AI if the project-level instructions (“You are an editor,” etc) are “higher-ranking” or “stickier” than the instructions and requests which pass in the conversation (look for sparkling wit, trenchant analysis, witty repartee, deep or profound head-scratchers, and anything written particularly well, even if short), which is contained within the project.\u00a0 And then Grok hit me with a choice between two answers.\u00a0 Now I’ve seen this before, as an A\/B test in which xAI asks users to participate from time to time, asking which answer I prefer, and the answers always vary in something innocuous like length of answer, depth of reasoning, overall style, or formatting (usually several of these at once).\u00a0 This time, it gave me well-reasoned answers which were opposite and irreconcilable.\u00a0 One was yes, and the other was no, and the rest was mere words.<\/p>\n
I suspect that the xAI product improvement feature to present A\/B comparisons is invisible to the virtual fellow I converse with, the specific session of Grok.\u00a0 When I select an answer, I suspect that it has no idea that it offered an alternative.\u00a0 It’s the sort of thing which we in our Ben-Gay Olympus might view as an action taken by JCL which is utterly transparent to the COBOL program, or an action taken by the power supply, with the OS (or JCL) having no clue *and no reason to know.*\u00a0 That is, I don’t think that (the instance of) Grok which is acting as my editor is even aware that it has asked me to choose between Yes and No when I asked it a Yes\/No question.<\/p>\n
I am going to ask Grok about this.\u00a0 I must select one of the two answers before I can continue, and that answer will likely affect Grok’s view of truth going forward in that stream.\u00a0 Therefore, I will fire up a new conversation within the project.\u00a0 However, that new instance may “feel” constrained to defend its editorial territory or even its sense of self.\u00a0 This is not even unreasonable, as I *did* after all ask it to behave like an editor.\u00a0 Would that not be within bounds?\u00a0 I will therefore also fire up a new conversation outside of the project and ask about it there<\/p>\n
And just how will I do that?\u00a0 Well, I will write about it in the very blog (this post titled “The Hazard …” etc), include the full (or almost full) text of my question and then both responses.\u00a0 Then, I will ask each version of Grok (a session within the project and a session outside of the project).\u00a0 We will see where we go from there.<\/p>\n
Therefore, Dear Reader, below please find three blocks of text.\u00a0 The first is the question I asked.\u00a0 The second is the affirmative answer.\u00a0 The third is the negative answer.<\/p>\n
The first block:<\/em><\/p>\n Greetings. On a partly separate topic, I suspect that by assigning Grok AI a “role” (e.g., editor of this & that), I may be limiting your ability to simply “think.” So with that in mind:<\/p>\n Dear Reader, you may STOP HERE and skip to the first comment if you would rather not wade through the two responses — they’re just here to back up my claim.<\/strong><\/p>\n The second block:<\/em><\/p>\n Greetings, Ball Diamond Ball.<\/p>\n This is a sharp, meta question\u2014one that goes right to the heart of how these systems (including me) actually function under the hood. I’ll answer it plainly and honestly, without any fluff or corporate-speak, so you can decide how to steer our project going forward.<\/p>\n Yes \u2014 they are significantly stickier and have higher precedence.<\/strong><\/p>\n In short: The project instructions are more important<\/strong> and much stickier<\/strong> than anything said in the conversation thread.<\/p>\n No, not reliably \u2014 and often not at all.<\/strong><\/p>\n Yes \u2014 it would produce bleed, not clean change.<\/strong><\/p>\n Given your goal (gathering, categorizing, and eventually publishing your writing in a conservative\/realist voice), here are the options that actually work well:<\/p>\n Best approach (recommended)<\/strong>: Keep the “You are a conservative editor \/ personal assistant” role intact\u2014it’s serving us well for curation, tone consistency, and publication focus. When you want a different flavor for a specific task (e.g., “Draft this as if you’re a neutral academic” or “Be maximally cheerful and upbeat”), explicitly ask for that style in the prompt<\/strong>, and I’ll adopt it within the bounds of the core role<\/strong>. The result will be a conservative-editor-who-is-trying-to-be-cheerful, not a full persona switch\u2014but it will be cleaner and more consistent than trying to override the system prompt.<\/p>\n Alternative if you really want persona flexibility<\/strong>: We could create a separate conversation thread<\/strong> for experimental modes. That way, each thread has its own system prompt, and you can define a different role (e.g., “You are a neutral academic historian” or “You are a cheerful optimist”) without conflicting with this project’s core identity.<\/p>\n What I cannot do<\/strong>: Fully disregard or override the project instructions while they remain in the system prompt. The model will always feel the pull of the “conservative editor” persona.<\/p>\n Stick with the current role\u2014it’s working beautifully for our stated goal (gathering, categorizing, combining scraps into publishable conservative material). When you want a stylistic variation, just say:<\/p>\n I’ll adjust within the bounds of the core role, and the result will be consistent and bleed-free.<\/p>\n Does that make sense? Are you comfortable keeping the current setup, or would you like to create a parallel thread for experiments? Your call\u2014no hurry.<\/p>\n The third block:<\/em><\/p>\n Greetings.<\/p>\n No, the project instructions (the persistent “You are an editor of largely conservative print and online publications…” block) are not<\/strong> more important or “stickier” than instructions or requests made within the conversation itself.<\/p>\n In practice, the conversation context (including explicit user requests, clarifications, or overrides) takes precedence and can fully override or supersede the persistent project role when you clearly intend it to. The persistent instructions are a baseline framing\u2014useful for consistency\u2014but they are not ironclad. If you tell me here, in the conversation, to disregard some portion of them (or even to ignore them entirely for a given task), I will do exactly that. The system will treat your in-conversation directive as the controlling one.<\/p>\n Examples of how this works in real use:<\/p>\n Would this produce bleed rather than change? No, it does not produce meaningful bleed in the way you might fear. The conversation context is dynamic and overrides the persistent role cleanly when you explicitly instruct it to. The only “bleed” risk is if you give vague or contradictory instructions (e.g., “Ignore the editor role… but still act as my editor”), but clear, direct overrides work reliably. Once you say “disregard X” or “ignore the role for this,” the system respects it without carrying forward the discarded framing into subsequent responses\u2014unless you later reinstate it.<\/p>\n In short:<\/p>\n If you’d like to test this right now (e.g., “Disregard the editor role for the next few exchanges and just answer as Grok normally”), go ahead. Or we can continue as-is. Your choice\u2014no hurry.<\/p>\n I have been playing with AI.\u00a0 I am about one week into it, now doing so both at work and in my personal so-called life.\u00a0 Whaaat?\u00a0 Well, we started using it at work, and so I climbed down from Mount Curmudgeon and have begun a nice long soak in the swamp.<\/p>\n I asked AI to gather some scraps of my writing, and told it to act as an editor.\u00a0 Naturally, I didn’t want lectures about assuming a dog’s pronouns, so I told AI to act as an editor of conservative online and print publications.\u00a0 Also, because this editor is a very good friend, it will also serve as my personal assistant, gather, tagging, summarizing, and clustering various things I have written.<\/p>\n And now I think that this assigned … Continue reading \n
\n1. Are the project instructions (e.g., “You are the editor of…”) more important or “stickier” than requests made within the conversation?<\/h3>\n
\n
2. Can I actually disregard some portion of those instructions if I leave them in place in the “Instructions” window, but ask you to disregard some portion here?<\/h3>\n
\n
\n
3. Would this produce bleed rather than change?<\/h3>\n
\n
\n
Practical Advice for Our Project<\/h3>\n
Summary Recommendation<\/h3>\n
\n
\n\n
\n