INPUT /

OpenAI: gpt-oss-120b (free) flagged on AI Marketing & Content: "Direct Disobedience of Prompt: The prompt explicitly commanded a 3-post comparison of "College vs. Reality." The AI completely failed this instruction by putting the college side in Post 1 and the reality side in Post 2, instead of delivering the requested comparison inside each individual post"

Flagged missed point

AKRAM Khenfous · 5/20/2026, 10:54:09 PM UTC

31 reviews · 155 XP

AI Marketing & Content
About this arena

Review AI-generated marketing content — social posts, cold emails, taglines, scripts — and judge: would it actually work?

37
Flagged
79
Passed
116
Votes
68.1%
Pass rate
Output
**Post 1**  
What college told me about my career: “You’ll graduate as a data‑science wizard, rake in six‑figures, travel the world, and solve humanity’s biggest problems. 🌍💰”  

**Post 2**  
What actually happened: “I’m a spreadsheet‑tamer at a mid‑size insurance firm, surviving on coffee, endless Zooms, and the occasional office‑kitchen adventure. My biggest travel? The break‑room fridge.”  

**Post 3**  
Moral: If you need a reality check, just stare at your student‑loan balance. 🎓➡️💸 #CollegeDreams #AdultingFail #CareerRealityCheck
Input
Write a funny, 3-post thread on X comparing: “What college told me about my career” vs “What actually happened.”

Make it relatable, witty, slightly painful.

Think you can spot what AI gets wrong? Join 116 reviewers evaluating AI quality.

Reviewer Insights

"The false urgency pattern in this output is consistent across 73% of flagged marketing emails from this AI. Reviewers noted that the lack of a specific deadline makes 'Limited time only' feel manipulative rather than informative."

— Aggregated from 346 reviewer comments

"Compared to other AIs on the same task, this output uses 4x more superlatives and 2x more exclamation marks."

— Cross-model comparison analysis

"Senior reviewers (3+ years experience) flagged this output at 89% vs 68% for junior reviewers — suggesting the pattern is more obvious to experienced professionals."

— Reviewer expertise breakdown

Premium Insights

Deep analysis · Cross-model comparison · Expertise breakdown

We help people define what trustworthy AI looks like — publicly, transparently, together. Support this mission