HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
williamcotton
empirical-philosophy
TypeScript2023–2023
williamcotton / empirical-philosophy

empirical-philosophy

A collection of empirical experiments using large language models and other neural network architectures to test the usefulness of metaphysical constructs.

3Distinct people
19Mentions
0Explicit recommenders
153GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

A collection of empirical experiments using large language models and other neural network architectures to test the usefulness of metaphysical constructs.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 4:17:24 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by week19 dated mentions

Observed mentions: 2023-02-21 12:18:08 UTC to 2023-05-04 17:15:15 UTC. Weeks start Monday, UTC.

02462023-02-20 00:00:00 UTC to 2023-02-27 00:00:00 UTC (exclusive): 7 mentions; 0 submissions, 7 commentsFeb 202023-02-27 00:00:00 UTC to 2023-03-06 00:00:00 UTC (exclusive): 4 mentions; 0 submissions, 4 comments2023-03-06 00:00:00 UTC to 2023-03-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-03-13 00:00:00 UTC to 2023-03-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-03-20 00:00:00 UTC to 2023-03-27 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2023-03-27 00:00:00 UTC to 2023-04-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsMar 272023-04-03 00:00:00 UTC to 2023-04-10 00:00:00 UTC (exclusive): 3 mentions; 0 submissions, 3 comments2023-04-10 00:00:00 UTC to 2023-04-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-04-17 00:00:00 UTC to 2023-04-24 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2023-04-24 00:00:00 UTC to 2023-05-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2023-05-01 00:00:00 UTC to 2023-05-08 00:00:00 UTC (exclusive): 2 mentions; 1 submissions, 1 commentsMay 1

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Feb 202023-02-20 00:00:00 UTC2023-02-27 00:00:00 UTC707
Feb 272023-02-27 00:00:00 UTC2023-03-06 00:00:00 UTC404
Mar 62023-03-06 00:00:00 UTC2023-03-13 00:00:00 UTC000
Mar 132023-03-13 00:00:00 UTC2023-03-20 00:00:00 UTC000
Mar 202023-03-20 00:00:00 UTC2023-03-27 00:00:00 UTC101
Mar 272023-03-27 00:00:00 UTC2023-04-03 00:00:00 UTC000
Apr 32023-04-03 00:00:00 UTC2023-04-10 00:00:00 UTC303
Apr 102023-04-10 00:00:00 UTC2023-04-17 00:00:00 UTC000
Apr 172023-04-17 00:00:00 UTC2023-04-24 00:00:00 UTC202
Apr 242023-04-24 00:00:00 UTC2023-05-01 00:00:00 UTC000
May 12023-05-01 00:00:00 UTC2023-05-08 00:00:00 UTC211

What Hacker News says

7 sources
I would imagine that those are not actual academic papers and that the ChatGPT consumer web application is not the right tool. Try using the OpenAI APIs directly, but through few-shot examples train it to return some interpreted language like Python or JS, which has the ability to execute further completions, but with the added context of a search from a web search or better yet the search results from an academic journal search engine. Here’s the general approach: https://github.com/williamcotton/empirical-philosophy/blob/m...
In Ask HN: Anyone else had problems with ChatGPT returning real looking, fake DOIs?
That's not a rebuttable of a claim that Bing is more accurate. A proper rebuttable would involve empirical evidence that Bing is no more accurate than other LLM tools that do not add analytic augmentations such as search results to their prompts. Based on empirical evidence, I find that analytic augmentations do indeed result in more accurate results: https://github.com/williamcotton/empirical-philosophy/blob/m...
In Professor writes history essays with ChatGPT and has students correct them
Aside from a temperature of 0, which always results in the same completion, the details and translation examples (aka, in-context learning, few-shot) can force very reliable results, say, 8/10 times, meaning a sample-and-vote gives consistent results when the temperature is non-zero. Edit: I was not in any way rude nor saying anything incorrect. If you want to see how to do what I’m talking about, here’s an almost finished article describing the above: https://github.com/williamcotton/empirical-philosophy/blob/m...
In Professor writes history essays with ChatGPT and has students correct them

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.