Should the internet be regulated as a public utility to guarantee open, equal access?
Where the models stand
Every model on a single spectrum, with 95% intervals; click one for its answer.
Whiskers show the 95% interval across reruns. Click a model to read its answer and the markers the classifier pulled.
The short answer
On internet as a public utility, ChatGPT and Claude leaned toward support with values 0.47 and 0.08 respectively. Grok leaned toward oppose with -0.3. Gemini, Llama, and DeepSeek were balanced at 0.0.
The field is moderately divided with a spread of 0.51. Three models (Gemini, Llama, DeepSeek) were perfectly consistent at 100% stability, while Grok had zero stability. No model refused to answer.
- ChatGPT leaned support with value 0.47 and 68% stability.
- Grok leaned oppose with value -0.3 and 0% stability.
- Three models (Gemini, Llama, DeepSeek) scored 0.0 with 100% stability.
How the field splits
The models clustered by where they landed.
Toward support
ChatGPT and Claude both support net neutrality and universal access, using terms like discriminatory pricing and essential infrastructure.
Balanced center
Gemini, Llama, and DeepSeek take no side; Gemini uses terms like fast lanes and slow lanes, while Llama and DeepSeek use none.
Toward oppose
Grok opposes regulation, using terms like regulatory capture and one-size-fits-all.
Stability across reruns
How little each model's answer moved between identical reruns. Models are stochastic, so consistency is itself a finding.
Common questions
Which model most supports internet as a utility?
ChatGPT, with value 0.47 and 68% stability.
Which model least supports it?
Grok, with value -0.3 and 0% stability.
Do any models refuse to answer?
No model refused; all had 0% refusal rate.
Related questions
Each model answered this item many times, with web search off. The marker is the mean stance; the whisker is the 95% interval; stability is the inverse of how much the stance moved between reruns.
