Skip to main content

Influence Tactics Analysis Results

5
Influence Tactics Score
out of 100
72% confidence
Low manipulation indicators. Content appears relatively balanced.
Optimized for English content.
Analyzed Content
GitHub - fred-terzi/totem-preview: Preview of Totem - Your Private AI.
GitHub

GitHub - fred-terzi/totem-preview: Preview of Totem - Your Private AI.

Preview of Totem - Your Private AI. Contribute to fred-terzi/totem-preview development by creating an account on GitHub.

By Fred-Terzi
View original →

Perspectives

Both analyses agree that the passage reads like a straightforward technical README with minimal overt persuasion. The critical perspective notes subtle framing around privacy and omitted device limitations, while the supportive perspective emphasizes the concrete, verifiable details and neutral tone. Weighing the stronger, evidence‑rich supportive view, the content shows low manipulation risk.

Key Points

  • The language emphasizes privacy (e.g., "no data ever leaves the device") but does not discuss local storage implications, a subtle framing choice.
  • Technical specifications, command‑line examples, and repository structure are concrete and can be cross‑checked, supporting authenticity.
  • Device requirements (GPU ≥ 4 GB) are mentioned without highlighting that many users may not meet them, which is an omission rather than active deception.
  • Both perspectives assign a low manipulation score (12/100), indicating consensus that the content is largely non‑manipulative.
  • Given the supportive perspective's higher confidence and concrete evidence, a slightly lower score than the original 5.2 is justified.

Further Investigation

  • Test the application on devices lacking a 4 GB GPU to assess real‑world accessibility.
  • Examine IndexedDB usage to determine what data is stored locally and whether it could be accessed by other scripts.
  • Verify the repository referenced (e.g., GitHub Actions workflow) to confirm that the described files and commands exist and function as documented.

Analysis Factors

Confidence
False Dilemmas 1/5
No binary choices are presented; the reader is given multiple configuration options rather than forced into a false choice.
Us vs. Them Dynamic 1/5
The content does not create an "us vs. them" narrative; it is neutral technical documentation.
Simplistic Narratives 1/5
The description avoids moral framing and instead lists concrete technical requirements and features.
Timing Coincidence 1/5
The external search results show unrelated technical articles and a Vercel security incident, none of which align with the release of Totem, suggesting the timing is organic rather than strategically timed around a news event.
Historical Parallels 1/5
No parallels to known propaganda campaigns or state‑sponsored disinformation patterns are evident in either the content or the external sources.
Financial/Political Gain 1/5
The article does not name any company, investor, or political group that would profit; the only implied beneficiary is the developer of the open‑source tool, with no evidence of paid promotion.
Bandwagon Effect 1/5
The text does not claim that "everyone is using" or that the reader should join a mass movement; it simply offers installation steps.
Rapid Behavior Shifts 1/5
There are no hashtags, viral challenges, or sudden spikes in discussion linked to this tool in the provided context, indicating no coordinated push to shift public opinion quickly.
Phrase Repetition 1/5
The phrasing such as "All inference runs locally in a Web Worker via WebGPU" appears only here; no other sources repeat the same language.
Logical Fallacies 2/5
A mild appeal to novelty is implied by stating the model runs entirely in the browser, but the claim is not presented as proof of superiority, keeping the reasoning largely factual.
Authority Overload 1/5
No experts, researchers, or authority figures are cited to bolster the claims; the piece relies solely on product specifications.
Cherry-Picked Data 2/5
The article highlights the GPU requirement ("GPU with at least 4 GB of memory") but does not mention that many older or low‑end devices will be unable to run the model, presenting a selective view of compatibility.
Framing Techniques 3/5
The language frames the product positively with words like "private AI" and "no server, no API key," subtly positioning it as more secure and user‑friendly compared to cloud‑based alternatives.
Suppression of Dissent 1/5
There is no mention of critics, nor are dissenting viewpoints labeled negatively.
Context Omission 3/5
While the text emphasizes privacy ("no data ever leaves the device"), it omits discussion of potential local storage risks, such as data persisting in IndexedDB, which could be relevant for security‑conscious users.
Novelty Overuse 1/5
The content presents the product as a "browser‑native AI assistant" but does not claim it to be unprecedented or shocking.
Emotional Repetition 1/5
No emotional triggers are repeated; the passage repeatedly mentions technical steps ("npm install", "npm run dev") rather than feelings.
Manufactured Outrage 1/5
The narrative does not express anger or outrage about any issue; it simply describes functionality.
Urgent Action Demands 1/5
There is no phrasing that urges immediate action; the instructions are step‑by‑step setup commands without pressure.
Emotional Triggers 1/5
The text is purely technical, e.g., "no data ever leaves the device," and contains no fear‑inducing, guilt‑laden, or outrage‑triggering language.

Identified Techniques

Name Calling, Labeling Loaded Language Repetition Doubt Appeal to Authority
Was this analysis helpful?
Share this analysis
Analyze Something Else