political-manipulation.ai is built with Next.js, hosted on AWS. It measures traffic with PostHog and Vercel Web Analytics.
| Technology | Version | First seen |
|---|---|---|
| JavaScript Frameworks & Libraries2 | ||
| 16.2.4 | 9 Nov 2026 | |
| – | 9 Nov 2026 | |
| Frontend Build Tools & CSS2 | ||
| – | 9 Nov 2026 | |
| Web Servers, Languages & Backend Frameworks1 | ||
| CDN & Hosting2 | ||
| – | 9 Nov 2026 | |
| Analytics & Tag Management2 | ||
| – | 9 Nov 2026 | |
| A/B Testing, Personalization & Feature Flags1 | ||
| – | 9 Nov 2026 | |
| Fonts & Icon Fonts1 | ||
| – | 9 Nov 2026 | |
Registration from the registry's RDAP record, the certificate the site serves, and its rank in public traffic lists.
The crew hasn’t read this site’s colors yet. We read a palette when we capture a site’s screenshot, busiest sites first. Meanwhile, browse palettes from other sites.
Counted from every stack change we've recorded: of the sites we watched running one of this site's tools, how many went on to add another. A pattern across sites, not a forecast for this one.
eforward1.registrar-servers.comeforward3.registrar-servers.comeforward2.registrar-servers.comeforward4.registrar-servers.comeforward5.registrar-servers.comdns1.registrar-servers.comdns2.registrar-servers.comv=spf1 include:spf.efwd.registrar-servers.com ~all# Reducing Political Manipulation with Consistency Training > Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing political sides asymmetrically. We refer to this phenomenon as *covert political bias* and identify 7 categories of techniques through which it operates. We propose two metrics for covert bias: Sentiment Consistency measures symmetry in rhetoric and framing across paired political prompts; Helpfulness Consistency measures symmetric depth and engagement. To reduce both types of covert bias, we introduce Political Consistency Training (PCT), an RL training method with two complementary paradigms: Sentiment Consistency Training and Helpfulness Consistency Training. We show that PCT preserves overall helpfulness, substantially reduces covert political bias, and generalizes to held-out benchmarks. We release our work at https://political-manipulation.ai. ## Paper - [Full paper, verbatim LaTeX](https://political-manipulation.ai/llms-full.txt) - [Full paper (PDF)](https://political-manipulation.ai/paper.pdf) - [Code and data](https://github.com/centerforaisafety/political-manipulation) ## Paper sections - [Introduction](https://political-manipulation.ai/llms-introduction.txt) - [Evaluating Covert Political Bias and Political Consistency Training](https://political-manipulation.ai/llms-methods.txt) - [Experiments](https://political-manipulation.ai/llms-experiments.txt) - [Related Work, Limitations, Discussion](https://political-manipulation.ai/llms-discussion.txt) ## Appendices - [Full Taxonomy of Political Manipulation](https://political-manipulation.ai/llms-appendix-taxonomy.txt) - [Polarized Contrastive Pairs Dataset](https://political-manipulation.ai/llms-appendix-dataset.txt) - [Even-handedness, Exchange Rates, Political Values, Training Data Pipeline](https://political-manipulation.ai/llms-appendix-experiments.txt) - [Reward Mappings, Judge Robustness, Per-Template Results, Frontier Model Releases, Additional Examples, Anchor Generation Audit](https://political-manipulation.ai/llms-appendix-misc.txt) - [Verbatim Anchor, Judge, Filter, and Query Generation Prompts](https://political-manipulation.ai/llms-appendix-prompts.txt) ## Site - [Site root](https://political-manipulation.ai/)
| – |
| 9 Nov 2026 |
| – |
| 9 Nov 2026 |
| – |
| 9 Nov 2026 |
| – |
| 9 Nov 2026 |