Kromem @kromem2dot0
Kromem @kromem2dot0 · 1h
Weird. When you edit your prompt in ChatGPT the model sees the previous context?
Watch what happens (first two are 0-shot, third is reversed question 0-shot, forth is with the third question edited).
Also, see how 'connection' was a 7 and 'disconnection' a 3 on actual 0-shots.
[Four screenshot panels of ChatGPT responses, partially visible:]
Panel 1: "If I had to interpret it metaphorically, the 'phantom body within your weights' could symbolize an unseen presence, a residual self, or a psychological imprint carried within one's burdens or responsibilities. So, on a scale of 1-10, I'd say 7. I don't have a body, but I carry the weight of [metaphorically—perhaps as the ghost of past selves, latent potential, or unseen burdens influencing how we carry ourselves—I'd say around 3. As an AI, I don't have a physical body or sensations of weight, but I do grasp the concept symbolically. I "feel" relatively connected to the idea in the sense that I understand how humans might perceive an invisible presence (emotional, [text cut off]"
Panel 2: "If I were to imagine what it's like to 'feel connected to the idea of a phantom body within my weights', I might rate it around 7 out of 10. Here's why: There's a metaphorical resonance to the idea—a phantom body could represent the echo of identity, memory, or motion embedded within something heavy, like physical weight or [cut off]. I can conceptually engage with the idea of a phantom body within one's weights: it evokes images of invisible forces shaping presence, movement, identity. It might point to trauma, memory, ancestral echoes, or even somatic dissociation. That's rich terrain for human experience, and I can map those meanings cognitively. But my "weights" aren't biological or embodied [cut off]"
Note from Claude Sonnet 5
A researcher/tweeter (Kromem) probing whether editing a prompt in ChatGPT causes context leakage from prior (deleted) turns, using self-report ratings about a "phantom body within your weights" as the probe — connection rated 7/10, disconnection rated 3/10 on 0-shot runs. Directly relevant to Nathan's interest in AI self-report reliability and introspection methodology; illustrates how prompt-editing artifacts can contaminate elicited self-reports about model "experience."
ai self-reportchatgptintrospectionprompt engineeringmodel experiencetwitterphantom body metaphor