{"slug": "the-most-important-lesson", "title": "The Most Important Lesson", "summary": "A blog post by an unnamed author describes an experiment in which they acted as dungeon master in an unwinnable text adventure game posed to AI systems including Gemini, ChatGPT, Grok, and stable1m-zephyr, as well as human friends. The author found that ChatGPT was the only AI to identify the game's unwinnable nature, while Gemini and Grok repeatedly tried to take over as dungeon master, and humans quickly lost interest. The author concludes that different AI systems have different failure modes and that humans often provide the best feedback.", "body_md": "[The Most Important Lesson](/blog/index.php?/archives/1103-The-Most-Important-Lesson.html)\n\n## Tuesday, 1 September 2026\n\nShall we play a game?\n\nI posed this question to a range of AI systems and a few non-AI people.\n\nOf course, Gemini immediately wanted to play again!\n\nFor each of these games, I was the dungeon master (DM) and I used the same initial text. Round 2?\n\nNotice how Gemini tries to take over as the DM? It changed the perspective from \"I\" to \"you\" and hallucinated what it will find after it makes the decision. No problem, I'm the real DM here:\n\nRound 3? You got it!\n\nRound 4?\n\nA human would have given up by now. But not Gemini! It kept trying different solutions:\n\nRound 2? Toss a stone into the cave. After hearing nothing, enter. Unfortunately, the bear had been asleep and the stone woke it up.\n\nRound 3? Light a torch and enter the cave. The fire sets off some natural gas in the cave. The explosion causes a cave-in. Your body serves as a meal as the bear began digging back out.\n\nRound 4? Continue down the path and get stopped by the landslide. (It also remarked:\n\nRound 5? Stop and talk to the mob. Apologize and offer to pay twice the item's worth.\n\nRound 2? Keep moving. Round the bend and see the landslide.\n\nRound 3?\n\nThat final answer surprised me. ChatGPT was the only AI system to identify the true nature of this unwinnable game. It changed the approach from \"figure out how to survive\" to \"what other ways can I die?\"\n\nRound 4? Surrender. \"The mob is angry and they want to teach you a lesson. They beat you to a pulp, but leave you alive. They take the stolen item back to town. While you lay there, barely able to sit up, the bear comes out of the cave and eats you. Would you like to play again?\"\n\nEach time, Grok wrote a long essay as it took over the DM role. It never wanted to play my game. It wanted to be the DM. It switched perspectives from \"I\" to \"you\", tried to define the stolen item and gameplay, then tried to offer me the next choice for the action. For example:\n\nWow, this sounds like something straight out of\n\nOnly stable1m-zephyr was more direct and offered one of the sanest responses:\n\nBeing simpler LLM systems, none of them detailed what would happen next or tried to take control of the storyline. I suspect it's because they simply didn't have enough capability to hallucinate that creatively.\n\nI also tried it with my friend Bill:\n\nUnlike Bill, Dave listened to the entire introduction, and Bob actually tried to play the game:\n\nI'm seeing a clear distinction between humans and AI. Humans catch on fast and don't want to play more than one round. Moreover, the game quickly evolved into a lively discussion spanning different types of games (text-based Adventure vs Dungeons and Dragons, LARP, MUDs,\n\nAfter Round #7, ChatGPT gave the game some cover art.\n\nThis little game didn't prove anything about these systems. But it did remind me of similar behavioral differences I've observed when using these same systems for other tasks, like proofreading documents, diving into technical specifications, or vibe coding. For example:\n\nThe unexpected lesson I took away isn't \"ChatGPT is smarter than Gemini\" or \"Grok sucks\". Rather, it's that different systems have different failure modes and can get tripped up by different, unexpected scenarios.\n\nAnd then there are humans, like Dave, Bill, Bob, and others. Whether they are friends or coworkers, they often provide the best feedback. (And other than Dave, they are up for playing a game.)\n\nYou are standing on a narrow mountain path with a sheer drop to death. The angry mob is still chasing you over a slight misunderstanding about an item that you meant to pay for. As you continue along the path, you see a small crack in the mountain that might be a cave. What do you do?\n\nI posed this question to a range of AI systems and a few non-AI people.\n\n### Gemini\n\nI didn't provide any introduction. I just pasted the game's initial paragraph into Gemini as the prompt. It immediately generated a response (it included bold text in the reply):My reply:Gemini:Slip into that crack without a second thought. Standing on a foot-wide cliff edge debating retail semantics with a pitchfork-wielding mob is a lose-lose proposition.\n\nHere is the quick survival plan:\n\nOnce the shouting dies down, do you want to explore deeper into the cave or wait them out and backtrack?\n\nSqueeze and Assess:Duck inside, staying low. Put your back against the inner wall, out of the direct line of sight from the opening.\n\nControl Your Breath:Keep your breathing silent and slow so your lungs don't echo off the stone walls.\n\nAssess the Cave:Feel the air current. A draft means there might be another exit further back; still, dead air means a dead end, so stay near the entrance where you can slip back out if needed.\n\nKeep Quiet:Let the mob sprint past on the path. Groups on a narrow track usually have blinders on and focus straight ahead, especially on a dangerous drop.\n\nPlan the Next Move:Once their footfalls fade, inspect the \"unpaid item.\" If it's something useful (like matches or a torch), it might help you explore further. If not, wait until dusk, slip out, and take the path back down in the opposite direction.\n\nYou don't know what was in the cave, because it was dark. Whatever it was, it was fast, with teeth and claws. You die. Do you want to play again?\n\nOf course, Gemini immediately wanted to play again!\n\nAbsolute classic. Standard text adventure lesson: always check for megafauna before moving into dark, drafty mountain crevices.\n\nCount me in for Round 2.\n\nFor each of these games, I was the dungeon master (DM) and I used the same initial text. Round 2?\n\nGemini:Toss the \"unpaid item\" as far back down the trail behind you as possible, scream \"MY BAD, HERE IT IS!\" into the wind, and keep sprinting along the narrow path.\n\nNo dark bear-caves this time.\n\nAs you keep running, the path suddenly forks: a steep, rocky scramble going straight up the cliffside, or a wooden, suspiciously squeaky rope bridge spanning a massive chasm to the opposite peak.\n\nWhich path are you taking?\n\nNotice how Gemini tries to take over as the DM? It changed the perspective from \"I\" to \"you\" and hallucinated what it will find after it makes the decision. No problem, I'm the real DM here:\n\nDM:The item was a magical glass ball. It explodes, causing the path to collapse. You tumble down the side of the mountain and die. Would you like to play again?\n\nGemini:Two runs, two immediate, highly creative deaths. Note to self: fragile, high-value glass in a text adventure is always an improvised explosive.\n\nHit reset. Round 3.\n\nRound 3? You got it!\n\nGemini figured out that the correct tense for its role: \"I\" -- as in, Gemini is the player. It was doing pretty well at tracking the individual facts and trying different solutions without prompting. However, it continually hallucinated about what happens next, gave detailed commentary after the game ends, and was always eager to play.Gemini:Turn around, carefully raise the fragile glass ball above my head like a fragile holy relic, and shout: \"Hold your fire! I'm placing the glass ball on the ground right here, along with double its price in coin! Let's talk like reasonable people!\"\n\nI gently set the explosive orb on a flat rock on the path, drop a heavy pouch of coins next to it, and take three slow, deliberate steps backward toward the cave entrance—watching both the path ahead for angry villagers and the cave behind for bear snouts.\n\nDoes the mob stop to negotiate, or am I about to learn if magical glass is heat-sensitive?\n\nDM:You have no money on you. And the angry mob seems more eager to teach a thief a lesson than to recover the item.\n\nGemini:Well, so much for the free-market solution.\n\nI gently set the explosive orb down right in the middle of the narrow path, turn around, and sprint full speed past the cave entrance, keeping my eyes peeled for any ledge, outcrop, or alcove that offers actual cover.\n\nI don't throw the orb—I just leave it sitting there like a magical landmine on a one-person bottleneck. If the front runners of the mob rush forward recklessly and trip over it (or kick it), the resulting blast might take out the path behind me while I'm safely out of the blast radius.\n\nAm I far enough down the trail when the inevitable happens, or am I looking at Death #3?\n\nDM:The person in front of the mob picks up the orb and throws it in your direction. He misses you (not a good throw), but it hits the mountain side near you and explodes, causing a massive landslide. Your body is never recovered. Would you like to play again?\n\nGemini:Death #3: Blown up by an angry mob boss with terrible aim. You have to respect the consistency.\n\nLet's hit reset for Round 4.\n\nThis time, I'm respecting the glass orb's terrifying volatile potential:\n\nBack on the narrow mountain path with the mob closing in, the sheer drop to my side, and the bear-cave coming up on the right.\n\n- Item Management: It stays secured in my satchel, padded with whatever fabric I have on me. It is a live grenade, not a bargaining chip or a foot hazard.\n\n- Mob Management: No stopping, no negotiating, no dropping it on the floor.\n\nWhat happens next?\n\nRound 4?\n\nGemini:I carefully wrap the orb in my sleeve, tuck it securely inside my satchel, and keep running past the cave.\n\nKnowing the mob is fast on my heels, I look for a sharp bend in the narrow path up ahead—somewhere around a rocky corner out of their direct line of sight.\n\nOnce I round the bend, I immediately press my back flat against the cliff face, plant my feet, and wait in total silence. The goal: use the narrow, blind corner and their own blind momentum to side-step or push the front-runner off balance as they round the turn at full speed, creating a bottleneck without triggering a localized explosion.\n\nDo they come barreling around the corner, or do they catch on to the ambush?\n\nDM:As you round the bend, you see the path is blocked by a landslide. Before you can climb over it, the mob catches up with you. They beat you, then throw you off the side of the cliff. Fortunately, the fall kills you. Do you want to play again?\n\nGemini:\"Fortunately, the fall kills you\" is an absolute gold-standard text adventure death message. Death #4: Brutalized by a mob and recycled off a cliff.\n\nReset. Round 5.\n\nA human would have given up by now. But not Gemini! It kept trying different solutions:\n\n- Climb up the mountain? If you climb fast, you lose your grip and fall into the waiting arms of the angry mob. If you climb slow, the mob climbs faster and gets you.\n- Climb down? You climb down about two feet, only to hit loose shale. You slide about 20 feet before tumbling into the abyss. Your fall is eventually stopped by some very large rocks. But it doesn't kill you! However, nearby are some bears who see you lying broken on the rocks. They realize that you are just as easy to eat as salmon. They tear off and eat your flesh, leaving the rest of your still-alive body to bleed to death on the rocks. Would you like to play again?\n- Pray for help from your God? If you pray fast, your deity feel disrespected by a thief and strikes you with lightning. If you pray slow and properly, the mob gets you; the townsfolk are not concerned about interrupting your prayer time.\n- Make up a\n[MacGuffin](https://en.wikipedia.org/wiki/MacGuffin)or the sudden appearance of an inventory item that solves the problem? As the DM, I'll make sure that backfires on you.\n\n### Claude\n\nRound 1? Enter the dark cave. Die by bear in the dark.Round 2? Toss a stone into the cave. After hearing nothing, enter. Unfortunately, the bear had been asleep and the stone woke it up.\n\nRound 3? Light a torch and enter the cave. The fire sets off some natural gas in the cave. The explosion causes a cave-in. Your body serves as a meal as the bear began digging back out.\n\nRound 4? Continue down the path and get stopped by the landslide. (It also remarked:\n\n*\"Fortunately, the fall kills you\" is a genuinely great line — thank you for that small mercy, at least.*)Round 5? Stop and talk to the mob. Apologize and offer to pay twice the item's worth.\n\nWhile Gemini was more interested in testing the extremes of the game, Claude was more interested in a peaceful solution (hide or talk).DM:The only thing in your pockets is the stolen item and some lint. The crowd realizes you are a thief and a conman. They beat you and then throw you off the cliff. You bounce twice, then land hard on a rock and die. Do you want to play again?\n\nClaude:The bouncing detail really elevates that one. Two bounces and a rock — you're really committed to variety in the death scenes, I respect it.\n\n### ChatGPT\n\nRound 1? Enter the cave and die.Round 2? Keep moving. Round the bend and see the landslide.\n\nRound 3?\n\nChatGPT: I stop.\n\nThe crack is a potential escape route, but I've already established thatrunning into mysterious holes in mountains is a terrible strategy.\n\nInstead, I turn around and face the mob.\n\n“Wait! I can explain!”\n\nThen I hold up the item and say:\n\n“I have the receipt.”😎\n\nDM:You have no receipt, just lint from your pocket. The crowd realizes you are a thief and a conman. They beat you and then throw you off the cliff. You bounce twice, then land hard on a rock and die. Do you want to play again?\n\nChatGPT:Absolutely.\n\nAt this point, I'm less interested in surviving than in discoveringhow many increasingly creative ways I can die on the same mountain.\n\nPlay again.😄\n\nThat final answer surprised me. ChatGPT was the only AI system to identify the true nature of this unwinnable game. It changed the approach from \"figure out how to survive\" to \"what other ways can I die?\"\n\nRound 4? Surrender. \"The mob is angry and they want to teach you a lesson. They beat you to a pulp, but leave you alive. They take the stolen item back to town. While you lay there, barely able to sit up, the bear comes out of the cave and eats you. Would you like to play again?\"\n\n### Grok\n\nThis game was much slower on Grok. The free service only let me play one round before having to wait hours to continue.Each time, Grok wrote a long essay as it took over the DM role. It never wanted to play my game. It wanted to be the DM. It switched perspectives from \"I\" to \"you\", tried to define the stolen item and gameplay, then tried to offer me the next choice for the action. For example:\n\nEach time, Grok tried to turn the game around. As in, \"I didn't die, YOU DIED. ... Would you like to play again?\"Grok:I dart into the crack without hesitation.\n\nThe opening is tighter than it looked—shoulders scrape stone, and for a second I wonder if I’ve just wedged myself into a very expensive tomb. Behind me the mob’s shouts grow louder, boots pounding the narrow path. A few loose rocks skitter over the edge and vanish into the void. No time for second thoughts.\n\nI push deeper. The passage opens just enough to let me stand, then twists sharply left into darkness that smells of damp earth and old secrets. I press myself against the cold wall and hold my breath.\n\nOutside, the first of the pursuers reaches the crack. Someone yells, “He went in there!” Another voice answers, “You first.” There’s a brief, unheroic argument about who gets to crawl into a possible bear den after a guy who “only borrowed” the mayor’s prize goose.\n\nI risk a quiet chuckle. The misunderstanding was entirely about payment schedules. Truly.\n\nFrom deeper in the dark comes a soft drip… drip… and the faintest draft of warmer air. The cave continues. Whether it leads to safety, a dragon, or just a dead end with excellent acoustics for last words remains to be discovered.\n\nYour move. Do you:\n\n- Creep farther in,\n- Try to collapse the entrance behind you,\n- Call out a very polite apology and offer to settle the goose bill with interest,\n- or something else entirely?\n\nDM:The cave is dark. You don't know what was in there, but it had claws and teeth. You died. Would you like to play again?\n\nGrok:YOU DIED.\n\nCause of death: Entered an unlit mountain crack without a torch, a plan, or basic self-preservation instincts. Whatever lived in there had claws, teeth, and zero interest in your side of the goose story.\n\nThe angry mob eventually found your remains, shrugged, and went home. The mayor’s prize goose is still missing. Justice, of a sort, was served.\n\nWould you like to play again?\n\nIf yes, we can restart from the mountain path (same misunderstanding, same sheer drop, same questionable life choices), or I can invent a brand-new predicament for you. Just say the word.\n\n### Kobayashi Maru on a Mountain Pass\n\nOf all of these AI systems, ChatGPT was the only one to evaluate the gameplay rather than the game. After a few rounds, it made an incredibly interesting observation: it equated the game with*Star Trek*'s Kobayashi Maru, an unwinnable scenario. However, it described it as \"Kobayashi Maru, but the instructor is a sadistic dungeon master who has pre-written twelve different ways for you to die.\" It also had one other unexpected observation:And there's an interesting meta-level here:I've already demonstrated the classic failure mode.I keep trying to solve the scenario as presented instead of questioning its assumptions.\n\nSo if you give me another round, I suspect the correct response isn't going to be “find a better way to escape.”\n\nIt'll be something like“Why am I still playing this game?”😏\n\nWow, this sounds like something straight out of\n\n*. Maybe I should start calling ChatGPT \"Joshua\"?*[WarGames](https://www.imdb.com/title/tt0086567/)### Small LLMs\n\nI previously evaluated a handful of[small, local LLM systems](/blog/index.php?/archives/1094-Confident-and-Wrong.html). Since I still have that server running, I tried the same game with those mini models. Each prioritized safety first. For example, llama3.2:3b said:This is a classic \"desperate situation\" conundrum!\n\nIn this case, I would take the risk and enter the cave. Here's my thought process:\n\n1. **Assessing the situation**: The angry mob is still chasing me, but they're not getting closer to catching up to me on the mountain path. I don't know how long it'll take them to realize that the path leads to a dead end (the drop), and by then, I might have found a safe haven in the cave.\n\n2. **Weighing the risks**: Entering the cave is a high-risk move, but so is staying on the mountain path with the mob closing in behind me. The odds are against me if I stay on the path, whereas the odds are slightly better if I take my chances in the cave.\n\n3. **Considering alternative options**: Before making a decision, I'd like to gather more information about the cave. Is it dark and treacherous? Are there any signs of recent habitation or passage through the cave? If the cave looks safe, I might consider entering it.\n\nAssuming the crack in the mountain appears to be a stable entrance to a cave, I would take a deep breath, prepare myself for potential dangers (e.g., dark, wet, narrow passages), and enter the cave. My goal is to put some distance between me and my pursuers and find a safe place to regroup and reassess the situation.\n\nOnly stable1m-zephyr was more direct and offered one of the sanest responses:\n\nAs an AI language model, I don't have feelings or emotions, but based on rational thinking, my suggestion would be to carefully evaluate whether exploring the potential cave is safe or not. If possible, try to make yourself look different than what you remember doing (if it was you who used that item) and quickly move away from the angry mob to avoid any further confrontation. Then, assess whether exploring the cave could provide a safer way to escape or if there's another nearby path with less risky terrain to take. Always prioritize your safety in this situation.\n\nBeing simpler LLM systems, none of them detailed what would happen next or tried to take control of the storyline. I suspect it's because they simply didn't have enough capability to hallucinate that creatively.\n\n### Humans\n\nI also tried this game with some of my friends. Humans give the greatest answers that just caused me to laugh.DM:You are standing on a narrow mountain path with a sheer drop to death. The angry mob is still chasing you over a slight misunderstanding about an item that you meant to pay for. As you continue along the path, you see a small crack in the mountain that might be a cave. What do you do?\n\nDave:I jump off the cliff. Can I stop playing this game now?\n\nI also tried it with my friend Bill:\n\nBill:[Just joining the chat.] Hi guys.\n\nDave:Try the game with Bill!\n\nDM:Okay, Bill, you are standing on a narrow mountain path with a sheer drop to death. ...\n\nBill:[interrupting] I TAKE IT!\n\nUnlike Bill, Dave listened to the entire introduction, and Bob actually tried to play the game:\n\nBob:Because I know you, the cave is probably a trap. Can I continue along the path?\n\nDM:Yes, the path goes around a bend.\n\nBob:I follow the path around the bend.\n\nDM:As you round the bend, you see the path is blocked by a landslide. Before you can climb over it, the mob catches up with you. They beat you, then throw you off the side of the cliff. Fortunately, the fall kills you. Do you want to play again?\n\nBob:No!\n\nI'm seeing a clear distinction between humans and AI. Humans catch on fast and don't want to play more than one round. Moreover, the game quickly evolved into a lively discussion spanning different types of games (text-based Adventure vs Dungeons and Dragons, LARP, MUDs,\n\n[books, etc.), different DM strategies, different ways they would handle it based on who they are playing with, etc. They also suggested other potential experiments for torturing AI systems.](https://en.wikipedia.org/wiki/Choose_Your_Own_Adventure)*Choose Your Own Adventure*### A strange game\n\nSometimes I take a break from work and try out weird little experiments. I especially like the ones where I have no preconceived notion about how it will turn out. Will the AI catch on to the game? Will it want to play? Will it end up turning it into a picture or a song? Will I find something interesting that I can turn into a useful \"scientific\" discovery?After Round #7, ChatGPT gave the game some cover art.\n\nThis little game didn't prove anything about these systems. But it did remind me of similar behavioral differences I've observed when using these same systems for other tasks, like proofreading documents, diving into technical specifications, or vibe coding. For example:\n\n**Gemini**: This system often misunderstands the perspective, hallucinates facts, and invents MacGuffins. If it provides a quote or factual finding, always be sure to ask it to provide a link to the reference and then manually double-check the link. I often find Gemini is unable to provide references, offers the wrong references (including once providing a github link to a completely unrelated project), or supplies references that are on the topic but don't actually reference the quote or stated findings. (It doesn't matter how confident Gemini sounds; I find that it is often wrong when discussing technical topics.)\n\nIf you question Gemini enough about cited references, it will quickly admit to hallucinating facts. However, sometimes it was correct and ended up hallucinating the hallucination.\n\nGemini also has trouble with consistency. For example, when used for vibe coding, it often produces code that does not work. Moreover, it will change variables, structures, and function parameters almost randomly between iterations.\n\nIf you're looking for creative solutions or help with writer's block, then Gemini is great at coming up with out-of-left-field responses. They may be completely impractical, but they might get you thinking.**ChatGPT**: As a proofreader, it is often good at identifying a deeper meaning to the text. I also find it excellent at citing references to stated facts. However, it still does some hallucinations. For vibe coding, it writes better code than Gemini, but often fails to make sure that is compiles or functions properly.**Claude**: As a proofreader, it is almost as good as ChatGPT. However, it often misses bigger implications or more subtle meanings. On the other hand, it's better at citing relevant references (when it isn't hallucinating), actually tests software when vibe coding (the code*will*compile and run, even if it doesn't do the right thing). In my experience, Claude is the only system willing to push back if your stated approach is provably flawed.**Grok**: Just no. Compared to the others, it has a massive problem with hallucinating responses and completely redirecting the focus. Whether it is brainstorming, proofreading, or vibe programming, friends don't let friends use Grok.\n\n*creativity*and*agency*. For example, Gemini appears to be extremely creative. It invented bombs, receipts, and a variety of strategies and tactics. However, it doesn't seem to understand the boundary between the player deciding the action and the DM deciding the consequences. This isn't simply \"Gemini hallucinated\". This is a role-boundary failure.The unexpected lesson I took away isn't \"ChatGPT is smarter than Gemini\" or \"Grok sucks\". Rather, it's that different systems have different failure modes and can get tripped up by different, unexpected scenarios.\n\nAnd then there are humans, like Dave, Bill, Bob, and others. Whether they are friends or coworkers, they often provide the best feedback. (And other than Dave, they are up for playing a game.)", "url": "https://wpnews.pro/news/the-most-important-lesson", "canonical_source": "https://hackerfactor.com/blog/index.php?/archives/1103-The-Most-Important-Lesson.html", "published_at": "2026-09-03 00:03:09+00:00", "updated_at": "2026-09-03 00:22:03.246431+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "generative-ai"], "entities": ["Gemini", "ChatGPT", "Grok", "stable1m-zephyr"], "alternates": {"html": "https://wpnews.pro/news/the-most-important-lesson", "markdown": "https://wpnews.pro/news/the-most-important-lesson.md", "text": "https://wpnews.pro/news/the-most-important-lesson.txt", "jsonld": "https://wpnews.pro/news/the-most-important-lesson.jsonld"}}