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.

Curious to see and talk with others about using AI to dynamically write personal novels as a hobby, a form of choose-your-own-adventure where you can offload part of the creativity and majority of the grunt-work involved with writing onto the AI.

I started around half a year ago with Novel AI, yet when my stories would reach around the 15,000 word count the context management required due to the 2k token limit caused for a a net negative experience. A few months ago I experimented with ChatGPT at its 4k token limit, but the major cons of the limited ability to edit the content combined with the "always happy" bias hard-wired in made it short lived. That is until I discovered the variant site, Open AI Playground in Chat mode. It isn't free, but the first $5 are free as a trial. (And technically they mention it isn't for entertainment purposes and to use it responsibly)

Using the Playground I've written a 41,000, 23,000, and 21,000 (in-progress, plan is to hit 6 digits) word count personal stories/novels/adventures thus far. Using the co-DM system of bouncing with the AI to suggest creative alternatives (e.g. "List 10 twists that could occur next in the story"), adding creative embellishments (e.g. "Describe the city in detail, using epic high-fantasy influence"), and many other tips it's kept me hooked on some wild adventures across my favorite genre(s), tailored to me.

Edit:
OpenAI just released a GPT 3.5 Turbo 16k model for the Playground, lol. Absolutely obliterating NovelAI's 2k and the previous 4k limits. You could fit a significant portion of an entire novel and it'd take into account every sentence said. It'd probably take a pretty penny to use even half the context window, but could be useful for more critical moments of my novels.