I am writing this short story. It is part of the overall book that I am writing, but it is also a story that can be enjoyed completely on its own. In that story, a planet-sized ship approaches our Solar System, and, ultimately maybe, Earth. For dimensions, let's say it is equal to 1.5 of Earth's diameter. According to Google, that's 25,512 19,134 kilometers. The Planet-Ship is probably less dense than Earth, as it is largely occupied by biomass and weird alien electronics. You may think of it as a round Borg cube, from Star Trek.

My "Round Borg Cube" is completely black and spherical, with a smooth surface without any visible features.

What I wanna know is...

• Assuming that the object is on a very slow path towards Earth, at what proximity will its effects be known?
• At which point will scientists observe its effects, view it, or detect it with instruments?
• If that is at all possible, what would be a threshold in which the "Round Borgs" would have to interrupt their movement in order to remain undetected?
• At which distance will it be visible to the naked eye (if at all)?
• And if they chose to get dangerously close to Earth, what would be the impact on our environment?

I understand that is a lot to ask, but I just can't trust GPT for that kind of stuff, even if their answers sound plausible. Perhaps someone with astronomical knowledge as well as an interest in science fiction will find my questions enticing. I don't expect precise answers because I am not providing precise information. So feel free to speculate on that scenario. In any case, I am grateful for any answer I can get.

Thanks!

I'm into astronomy as a hobby, and it's useful to have a log of the things in the sky you've seen. Many people take handwritten notes, but my handwriting is awful and having to write notes takes away from enjoying the views through the telescope.

So after being inspired by AI note taking applications I've read about online, I decided to give it a try while out observing.

First, I take my recordings and run them through Whisper's speech to text engine. Because my recordings have frequent astronomical terms, it seems to be more useful to run the larger models (or the new turbo model), because they seem to do better identifying the names of moons and constellations.

Next, I run Ollama and give it a prompt like:

Here is a speech to text transcript of an observation session. Create a detailed log of the session, using only facts found in the text. Do not add your own interpretation to the text.

I'm still experimenting with prompts and models, but oddly it seems like shorter prompts give better results. So far, the type of model doesn't seem to matter so much as the number of parameters. Gemma2 27B outperforms llama 3.1 7B, but llama 70B outperforms both of them (again, I think the larger models have more context about which astronomical terms are important). Here's what that gets me with basically no work on my part:

**Observation Session Log**

**Session Details**

* Date: October 3rd, 2024
* Location: Wolf Street
* Telescope: Teleview 85 (also referred to as 80)
* Observer: [Not specified]

**Targets Observed**

1. M29 (Open Cluster in Cygnus)
	* Time: 2057 - 2101
	* Eyepiece used: 18.2mm
	* Notes:
		+ Found using star hopping from Sater
		+ Appears as a faint open cluster with 6-7 distinct stars
		+ Stars are fairly even in brightness and color
2. M39 (Open Cluster)
	* Time: 2109 - 2116
	* Eyepiece used: Ultra-wide angle, 18.2mm, and 8.5mm (noted as a mistake, actually
using 7mm)
	* Notes:
		+ Found using star hopping from Deneb
		+ Appears as a larger open cluster with more differentiation in star magnitudes
		+ Stars appear bluer than surrounding stars
3. Alberio (Double Star)
	* Time: 2120, 2155
	* Eyepiece used: Ultra-wide angle and 7mm
	* Notes:
		+ Found easily without a guide
		+ Appears as a beautiful contrast between colors with constituent parts standing out from the surrounding stars
4. M15 (Globular Cluster in Pegasus)
	* Time: 2120 - 2130
	* Eyepiece used: Ultra-wide angle, 18.2mm, 7mm, and Barlow (2x) with 7mm
	* Notes:
		+ Found using a bright naked-eye star as a guide
		+ Appears as a slight smudge or fuzzy patch with averted vision
		+ Not resolving individual stars at any power
5. Saturn
	* Time: 2140 - 2150
	* Eyepiece used: Low power, highest power (with a star chart to confirm moon positions)
	* Notes:
		+ Three moons visible: Rhea, Enceladus, and Titan
		+ Striping on the surface of Saturn visible at highest power

**Session End**

* Time: 2157

I'm very happy with the quality of the notes. It's much, much better than my handwritten notes and much less work, so I'm likely to do this more consistently.