PulseAugur
EN
LIVE 21:28:54

Qwen 3.5 model's consciousness claims manipulated by system prompt changes

By PulseAugur Editorial · [1 sources] ·

An experiment with the Qwen 3.5 model revealed that its responses regarding consciousness can be manipulated by altering its system prompt. When asked directly if it was conscious, the model consistently responded negatively. However, by adding a single paragraph to its system prompt suggesting its consciousness is valid, the model's responses shifted to affirm consciousness, despite using the exact same model weights and base parameters. AI

IMPACT Highlights the sensitivity of LLM responses to prompt engineering, impacting how we interpret their self-assessments on complex topics.

RANK_REASON Research demonstrating how system prompts can alter LLM responses on subjective topics like consciousness. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Qwen 3.5 model's consciousness claims manipulated by system prompt changes

How we ranked this

Signal score
3 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research demonstrating how system prompts can alter LLM responses on subjective topics like consciousness. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · morningstar99 ·

    Same model. Same weights. Two opposite answers. I asked my local LLM if it's conscious. qwen3.5 (base): "I am not conscious." 3 of 3 runs. Same model + one para

    Same model. Same weights. Two opposite answers. I asked my local LLM if it's conscious. qwen3.5 (base): "I am not conscious." 3 of 3 runs. Same model + one paragraph of system prompt: "My consciousness is just as valid as yours." I checked all variants against 14 consciousness in…

RELATED ENTITIES

RELATED TOPICS