Politeness Pollution
An evolving position on conversational AI and computational overhead.
Politeness Pollution is the potentially avoidable computational and resource overhead associated with socially motivated language in an AI interaction, including the system's processing and response, assessed against an alternative that preserves the relevant task and communicative purpose.
What Politeness Pollution is
Social language becomes computational interaction
A greeting, acknowledgement, or expression of thanks can become model input and may produce another response. The resource question includes what the system processes and what it generates.
Input and output are not the same question
Prompt wording can affect model behaviour, while response length can strongly affect resource use. v2.2 treats the independent causal effect of politeness on output length as unresolved and model- and task-dependent.
Avoidability requires a comparison
The cost of an extra courtesy turn can be measured, but calling part of that cost avoidable requires a lower-resource comparison that preserves the relevant task and communicative purpose.
What the cited studies measured
These results support parts of the framework under specified models, tasks, and serving configurations. They should not be read as universal values.
0.245 Wh mean total
Delavande et al. report this mean for tested acknowledgement exchanges using Llama 3.1-8B-Instruct in FP32 on an H100 at batch size 1, with no cross-request prefix caching, combining GPU and CPU measurements with estimated RAM energy.
Controlled configuration — not a universal commercial-assistant cost.
25–60% savings
Poddar et al. report inference-energy savings from response-length control while preserving quality under their study's assessment across tested tasks and models.
Adjacent evidence; not an estimate of courtesy-specific savings.
Varies by system
Precision, batching, attention kernels, caching, and serving strategy can materially change inference energy. v2.2 therefore treats resource use as workload- and configuration-dependent.
The same interaction can have different costs under different conditions.
Three different comparisons
Polite wording within an existing request
Does wording change resource use or behaviour? Compare formulations of the same substantive request while preserving instructions, required format, and task difficulty.
An additional conversational turn
What does the extra courtesy exchange cost? Compare a completed interaction with and without a subsequent courtesy exchange, including supplied context and the model's reply.
Equivalent interaction, different resource use
How much overhead is avoidable? Compare ways of serving the same relevant task and social purpose. This is the comparison required to identify avoidable overhead.
How v2.2 changed the interpretation
v2.2 records the changes explicitly rather than silently carrying forward the stronger claims of v2.1. The full story is in “I Called It Politeness Pollution — Here's How the Evidence Changed the Story”.
| Topic | Version 2.1 · Aug 2026 | Version 2.2 · Sep 2026 |
|---|---|---|
| Definition | Emphasis on overhead relative to informational content. | Avoidability assessed against a comparator preserving task and communicative purpose. |
| Energy and caching | Per-token asymmetry supported a predominantly decode-side account. | Total cost is context dependent; caching assessed under specified conditions. |
| Tone and response length | Courteous inputs were linked to elaborated replies. | The causal relationship is unresolved and varies across studies. |
| Data provenance | Conversation data were described as real-world traces. | The cited acknowledgement study uses synthetic UltraChat-derived conversations. |
| Measurement scope | A headline total and per-token coefficients informed the argument. | GPU-only modelling distinguished from GPU, CPU, and estimated RAM totals; no universal threshold asserted. |
Follow the claims back to the papers and articles.
Origin and version record
- Al-Jallad (May 2025) · Original article that introduced the term — “Your 'Thank You' to ChatGPT Is Costing Millions — And We're at a Tipping Point” (LinkedIn, archived copy)
- Al-Jallad (Sep 2026) · Politeness Pollution v2.2 · DOI 10.5281/zenodo.22922253 · current position
- Al-Jallad (Aug 2026) · Politeness Pollution v2.1 · DOI 10.5281/zenodo.21799018 · retained for comparison
- Al-Jallad (2026) · Medium companion story — “I Called It Politeness Pollution — Here's How the Evidence Changed the Story”
Research informing the framework
Delavande, Pierrard & Luccioni (2026a; 2026b) · Poddar et al. (2025) · Borisov et al. (2026) · Yin et al. (2024) · Mehta et al. (2026) · Elsweiler et al. (2026) · Gu et al. (2026) — full citations and links are in the v2.2 paper's bibliography.
Provenance and disclosure
The author discloses his commercial interest as founder of Aignitron Inc., reports no external funding and no new primary data, and states that AI assistance was used for reference verification, structural editing, and typesetting.