Kye Fox kyefox

Gemini 3 Fast: Collecting specific imagery and filter data for Venus flybys is a task of navigating archival data across decades of space exploration. Below is the breakdown for every major probe that performed a flyby of Venus and returned imagery.

Quick Resource: The Primary Repositories

NASA PDS (Planetary Data System): The "master" archive for NASA missions (Galileo, Cassini, MESSENGER, Parker). pds-imaging.jpl.nasa.gov
ESA PSA (Planetary Science Archive): The archive for BepiColombo and Solar Orbiter. archives.esac.esa.int/psa/
NSSDC (National Space Science Data Center): For legacy missions (Mariner). nssdc.gsfc.nasa.gov

So, this guy: https://lifehacker.com/tech/googles-co-founder-says-ai-performs-best-when-you-threaten-it

Run a search on the research: is there a better way to tickle the vectors that produce better outputs without being an asshole to a computer?

Great question, and there's a lot of actual research to unpack here. The short answer: no, you don't need to be an asshole to a computer to get good outputs. Threatening works a little, sometimes, for the wrong reasons, and there are much better levers to pull.

What Brin actually said (and what happened when researchers tested it)

name

xkcd-2501

description

Audit a piece of writing for expert blind spots — terms, concepts, or context that the writer has unconsciously treated as common knowledge, but which the target audience may not share. Based on xkcd 2501 "Average Familiarity": even when experts consciously try to simplify for a general audience, they still massively overestimate what readers know. Use this skill whenever the user wants to check if their writing is accessible to a specific audience, asks "will people follow this?", wants a jargon or assumed-knowledge review, or supplies a draft and a target reader. Also trigger when the user says "I tried to make it accessible but I'm not sure", or pastes something technical and wants to know what a non-expert reader would stumble on.

xkcd 2501: Average Familiarity Audit

The Problem This Skill Solves

name

provocateur-loop

description

Automates the "LLMs will never be able to do X" social media grift loop. Use this skill whenever the user wants to generate provocative AI-skeptic claims to bait developers into building skills, extract skills from demonstrations, or run the full automated provocation-extraction cycle. Trigger on phrases like "bait someone into building", "copy that skill", "provocateur loop", or any request to automate the skill-harvesting workflow.

The Provocateur Loop

A skill for automating the full cycle of:

Generating a provocative "LLMs can never do X" claim
Identifying when someone has proven you wrong by building a skill

This is good stuff, and why I always say inspired or informed by when prompting. It brings in the stuff trained on their works, but creates a new conceptual "thing" to represent the aggregate.

Can the panel weigh in on the ethics of using an LLM's neural network trained on experts' work like a search engine, to find and summarize their ideas to aid research? I think back to the Star Trek: The Next Generation scene where Geordi used the holodeck to create the ship's designer from what was known about her to have an interface to access that data. That seems in line with what I'm doing here, but what happens when, like Geordi, it goes too far?

Below is how each panelist—representing humanities, computing, and philosophy—might weigh in on your question of using a large language model (LLM) as a stand-in for real experts, touching on the Star Trek: TNG analogy with Geordi and Dr. Leah Brahms.

Write a python script to scrape all linked files of a certain file extension on a web page under the same domain as the page. Follow best practices. Handle errors, make strings OS-independent, etc. Be persnickety. Be pythonic.

Certainly! Below is a Python script that scrapes all linked files with a specified file extension from a given webpage and ensures they are from the same domain. This script uses requests to fetch web content and BeautifulSoup from bs4 for parsing HTML. It also handles errors gracefully, sanitizes paths, and follows best practices.

First, make sure you have the necessary packages installed:

pip install requests beautifulsoup4 urllib3

	11 of them got abbreviated by PowerShell, but not so much that you can't tell what it is.

	Band\1 - Horns\Alto Saxophone.nki
	Band\1 - Horns\Baritone Saxophone.nki
	Band\1 - Horns\Sax Section.nki
	Band\1 - Horns\Tenor Saxophone.nki
	Band\1 - Horns\Trombone Section.nki
	Band\1 - Horns\Trombone.nki
	Band\1 - Horns\Trumpet Mute.nki
	Band\1 - Horns\Trumpet Section.nki