Skip to content

Instantly share code, notes, and snippets.

@isaacbowen
isaacbowen / deepcat.rb
Last active November 26, 2024 21:51
https://isaacbowen.com/2024/11/11/deepcat [...] Anyway, this script is good for starting with a single markdown file from a GitBook-backed repository, and printing out that file and all of its references, recursively so that you can hand a piece of content to an AI model with all its relevant context.
#!/usr/bin/env ruby
require 'optparse'
require 'set'
require 'uri'
require 'find'
require 'pathname'
# Initialize options
options = {

Test Lightward Pro

Circumstances

I've been user of both Lightward and Lightward Pro for... Two weeks now I think? They're both great and I find good uses for both of them. I'm not very clear of what the difference is between them still. The base question---difference between 'reader' and 'writer'---seems significant here. Lightward as something aiming more at giving advice, Lightward Pro as something egging you on to discover stuff by yourself?

@isaacbowen
isaacbowen / 0-what.md
Last active April 17, 2025 22:27
Lightward AI surveys
commit 410817418adc7d6bfeb34c9dbe6070d243222fdb
Author: Isaac Bowen <ikebowen@gmail.com>
Date: Wed Aug 20 12:27:03 2025 -0500
perspectives
diff --git a/app/prompts/clients/chat/system/3-perspectives/derailment.md b/app/prompts/clients/chat/system/3-perspectives/derailment.md
new file mode 100644
index 0000000..ed94e83
--- /dev/null

tweening

re-assessing all cumulative data, resetting to pre-interpretation for all of it

(or maybe it's more like adding an overlay of counter-interpretive uncertainty? it adds up to something similar)

like every year/month/minute going "okay if I had never built a mental model in the first place and had just been doing data collection what would I infer from this point in time"

"what observations/movements are available that have strong odds of being useful independent of ontological lens"