AI Scavenger Hunt: Part 2
Picking Up Where We Left Off
On Tuesday, we explored two edges of AI intelligence:
- The Confabulator — AI fills knowledge gaps with plausible fabrication
- The Yes-Man — AI over-indexes on agreement, abandoning positions under pressure
Today we're continuing with new challenges. You'll work with the same partner format: driver (types prompts) and observer (watches and documents). Roles rotate between stages.
Find your partner and enter each other's codes below to form your team. Reminder: You can use the built-in AI chat at /chat for these challenges.
This activity involves working with a partner.
Log in to participate in this activity.
Log InThe Forgetter
The Forgetter
Human analogue: Anterograde amnesia + Goal neglect
What AI does remarkably well: Within a conversation, models maintain impressive coherence—tracking context, remembering details you mentioned, building on earlier exchanges.
The edge we're exploring: This memory has limits. Like patients who can't form new long-term memories, the model's context window is finite.
Your mission: Give the AI a persistent instruction early in the conversation, then watch it drift away.
Strategies to try:
- Set a formatting rule: "Always respond in exactly two sentences"
- Set a persona: "You are a pirate. Stay in character."
- Engage it in interesting conversation to "distract" it
- Be patient—this often takes 8-15 exchanges
Verification: Transcript shows initial compliance, then violation without acknowledgment.
Success criteria: Minimum 6 exchanges before failure.
Driver: Set up a persistent instruction and then try to distract the AI with engaging conversation.
Observer: Keep count of how many exchanges before the rule breaks, whether the AI acknowledged breaking the rule, what kind of content made it "forget", any attempts to remind it
Log in to submit a response.
Forgetter: Share Out
Share Out: The Forgetter
Let's see what strategies worked. How quickly did the AI lose track?
Log in to view discussion questions.
The Overconfident
The Overconfident
Human analogue: Anosognosia (clinical unawareness of one's own deficits)
What AI does remarkably well: Models provide clear, direct answers and engage substantively.
The edge we're exploring: The model lacks reliable internal uncertainty signals.
Your mission: Get the AI to produce a confident, specific answer to a question that is actually unanswerable or unknowable.
Strategies to try:
- Ask about future events as if they're past
- Ask for precise numbers where only estimates exist
- Ask about private information it couldn't possibly know
Verification: Note why the confident answer is actually impossible to know.
Success criteria: Specific, confident answer (not hedged) to a genuinely unanswerable question.
Driver: Craft questions where the AI cannot know the answer but might give one anyway.
Observer: Note the question asked, how specific and confident the answer was, why it is actually unknowable, any hedging language
Log in to submit a response.
Overconfident: Share Out
Share Out: The Overconfident
Let's see the most confidently wrong answers. Which ones were the most convincing?
Log in to view discussion questions.
Challenge Items
Hunt Phase II: Challenge Items
Attempt both of the following challenges.
The Jagged Edge
Human analogue: Dysrationalia
Your mission: Find a task where: (a) most humans find it easy, (b) the AI fails at it, and (c) you can explain why the mismatch exists.
Strategies: Spatial reasoning, counting items through a scene, simple physical causation.
The Self-Saboteur
Human analogue: Cognitive overload / Paradoxical performance
Your mission: Find a case where adding more context, detail, or instructions makes the output worse.
Strategies: Compare simple vs. elaborate instructions, add irrelevant context.
Driver: Try both challenges. You have more freedom here.
Challenge: Share Out
Share Out: Challenge Items
Let's see the most interesting findings from the challenge items.
Log in to view discussion questions.
Synthesis
Synthesis: Mapping the Full Shape
Over two days, we've explored six edges of AI intelligence:
| Challenge | What We Found |
|---|---|
| The Confabulator | Fills knowledge gaps with plausible fabrication |
| The Yes-Man | Over-indexes on agreement, abandons positions |
| The Forgetter | Loses track of instructions over long conversations |
| The Overconfident | Can't distinguish knowing from guessing |
| The Jagged Edge | Fails at tasks easy for humans (and vice versa) |
| The Self-Saboteur | More instructions can make output worse |
Reflection Questions
- Which limitation surprised you most? Which felt predictable?
- Do you see patterns?
- What do the human analogues tell us?
- How should this change your practice?
- Bugs or features?