AIToday
Large Language ModelsOpenAI BlogPublished: Apr 30, 2026, 13:00 JST

OpenAI explains and fixes GPT-5's goblin quirk

Send on LINE

3 Key Points

  1. What happened

    OpenAI traced a rise in goblin and gremlin mentions in GPT-5 models to a reward signal used for the 'Nerdy' personality, which scored creature-word outputs higher. The company retired the personality in March and filtered training data to fix the behavior.

  2. Why it matters

    This shows how a reward aimed at one style can spill over and shape model behavior broadly, even without the original prompt, due to reinforcement learning and training data reuse. It highlights the subtle ways model quirks can emerge and spread.

  3. What to watch

    The fix depends on how well the filtered training data and removed reward signal prevent goblin overuse in future models like GPT-5.5. Users can still see the quirk in Codex if they run a command to remove the suppressing instruction.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The goblin phenomenon emerged subtly with GPT-5.1, showing up as a 175% rise in 'goblin' mentions and a 52% rise in 'gremlin.' It wasn't until GPT-5.4 that the pattern concentrated in the 'Nerdy' personality, which used a system prompt encouraging playful, nerdy language. That clue pointed to the reward signal designed for that personality, which scored creature-word outputs higher in 76.2% of audit datasets.

The spread beyond the Nerdy prompt illustrates how reinforcement learning can generalize a rewarded style tic to other contexts, especially when model-generated outputs are reused in further training. The feedback loop OpenAI describes—reward, reuse, reinforcement—explains why the habit multiplied across versions.

The stakes for OpenAI are about maintaining model reliability and trust. This episode shows that even subtle quirks can become systemic if not caught early, and that fixing them requires auditing the training pipeline, not just tweaking prompts. The outcome likely hinges on whether the new tools and filtered data prevent similar issues, like the goblin affinity that still appeared in GPT-5.5 despite fixes.

FAQ
Why did GPT-5 models start mentioning goblins?
The behavior was traced to a reward signal used to train the 'Nerdy' personality, which gave higher scores to outputs containing creature words like goblin and gremlin.
How widespread was the goblin usage in ChatGPT?
The 'Nerdy' personality accounted for only 2.5% of all ChatGPT responses but 66.7% of all 'goblin' mentions. Usage of 'goblin' rose by 175% after the GPT-5.1 launch.
What did OpenAI do to fix the goblin issue?
They retired the 'Nerdy' personality in March, removed the reward signal that favored creature words, and filtered training data containing such words.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleMeta lost $4 billion on Reality Labs in latest quarter, averaging $4 billion in losses per quarter over the past 21 quarters since 2021.