Hacker News: foxhop

Introducing SLOP

foxhop — Sun, 23 Mar 2025 11:59:58 +0000

Article URL: https://russell.ballestrini.net/introducing-slop/

Comments URL: https://news.ycombinator.com/item?id=43452366

Points: 1

# Comments: 0

New comment by foxhop in "Genomic study: our capacity for language emerged at least 135k years ago"

foxhop — Mon, 17 Mar 2025 11:08:16 +0000

It is impossible to figure this out and it's dumb to try to give a number. We don't think Neanderthals could speak? They also had languages.

New comment by foxhop in "Out of Africa: celebrating 100 years of human-origins research"

foxhop — Mon, 10 Feb 2025 20:02:08 +0000

You scam artists are not fit for civilized society.

New comment by foxhop in "Out of Africa: celebrating 100 years of human-origins research"

foxhop — Mon, 10 Feb 2025 15:00:38 +0000

Politically motivated bollocks.

The white colonizer did not get colonized by tribes in Africa.

New comment by foxhop in "We are destroying software"

foxhop — Sat, 08 Feb 2025 19:58:12 +0000

For somebody who cares about software why are you advertising for disqus comments? Link in bio to a public domain commenting system forn static sites.

New comment by foxhop in "Reverse-engineering and analysis of SanDisk High Endurance microSDXC card (2020)"

foxhop — Sun, 02 Feb 2025 13:36:13 +0000

When i buy 512G microsd it becomes my property. If i need to repair or replace my property, it should be disclosed what technology i bought, so that i or my repairman could understand my property enough to decide a proper path forward depending on my data & other environmental devices.

The author needed to reverse engineer what could have been on the spec sheet...

New comment by foxhop in "Yek: Serialize your code repo (or part of it) to feed into any LLM"

foxhop — Sun, 19 Jan 2025 12:16:04 +0000

`tree --gitignore && cat .py && cat templates/`

New comment by foxhop in "Campsite switches to Creative Commons Non-Commercial license"

foxhop — Tue, 14 Jan 2025 11:15:38 +0000

I don't like lawyers so I use public domain.

Also code is like math which is public domain.

Public Domain File Uploads for Humans and Agents

foxhop — Tue, 07 Jan 2025 15:53:36 +0000

Article URL: https://git.unturf.com/engineering/unturf/upload.unturf.com

Comments URL: https://news.ycombinator.com/item?id=42623718

Points: 1

# Comments: 0

New comment by foxhop in "Things we learned about LLMs in 2024"

foxhop — Wed, 01 Jan 2025 11:40:50 +0000

Step 1: curate a context window of code from different repos (poke team about switching to mono repo)

Step 2: write a slack style message as if you are discussing the solution with a teammate that you have authority over as a delegate to get shit done & to revise as needed.

Step 3: press enter, LLM does something you don't like, delete history, fix prompt in step 2 and ask again, rinse and repeat until you have working code.

Step 4: ask for the changes to be written as a bash file that cat EOF all the files that change into place, run the script.

Step 5: git diff & play test the changes using functional testing (use your mouse & keyboard test the code paths that changed...)

Step 6: continue prompting & deleting history as needed to refine.

Step 7: commit code to repos

New comment by foxhop in "Ruby-refrigerator: Freeze all core Ruby classes"

foxhop — Tue, 31 Dec 2024 15:03:49 +0000

I was just thinking about something like this for very small web applications (1,200 line app.py & 600 lines of html templates), something lighter than requiring a working docker install.

a handful of dependencies (mostly Pyramid based at the moment) & whatever dependencies those have, pull it all down & serve it out of a tarball or zip file of a portable virtualenv.

New comment by foxhop in "Ibis: Federated Wikipedia alternative"

foxhop — Sun, 27 Oct 2024 19:10:15 +0000

If the maintainers are reading this is cool. I would start with an exporter/importer for pages from Wikipedia format into whatever format you use, it should also deal with the media. This is no small task but what you need.

New comment by foxhop in "Free Hermes AI ai.unturf.com and uncloseai.js"

foxhop — Tue, 22 Oct 2024 14:13:25 +0000

fun app another contributor made:

* https://beetoochat.glitch.me/

New comment by foxhop in "Free Hermes AI ai.unturf.com and uncloseai.js"

foxhop — Tue, 22 Oct 2024 14:11:41 +0000

My last post got shadow banned hard so trying again without the "Show HN:" moniker because I think that was the only thing I might have done wrong.

https://news.ycombinator.com/item?id=41895582

Free Hermes AI ai.unturf.com and uncloseai.js

foxhop — Tue, 22 Oct 2024 14:11:41 +0000

Article URL: https://russell.ballestrini.net/free-hermes-ai-unturf-com-uncloseai/

Comments URL: https://news.ycombinator.com/item?id=41914500

Points: 1

# Comments: 2

New comment by foxhop in "Show HN: Client Side anti-RAG solution"

foxhop — Sun, 20 Oct 2024 18:46:45 +0000

the proxy/server accepts any API key. I expect people to copy this infra with their own domains, this is a working proof of concept.

Show HN: Client Side anti-RAG solution

foxhop — Sun, 20 Oct 2024 14:28:26 +0000

Client Side Only Example, chat with this page.

Because we don't use API keys we don't have any real need for a server.

view the page source, it's _all_ there!

The program doesn't take history into account & yet is has surprising coherence.

View Source and start on line 258.

Comments URL: https://news.ycombinator.com/item?id=41895582

Points: 7

# Comments: 2

New comment by foxhop in "Llama 3.2: Revolutionizing edge AI and vision with open, customizable models"

foxhop — Wed, 25 Sep 2024 22:39:10 +0000

The llama 3.0, 3.1, & 3.2 all use the TikToken tokenizer which is the open source openai tokenizer.

New comment by foxhop in "Llama 3.2: Revolutionizing edge AI and vision with open, customizable models"

foxhop — Wed, 25 Sep 2024 22:34:52 +0000

4090 has 24G

So we really need ~40B or G model (two cards) or like a ~20B with some room for context window.

5090 has ??G - still unreleased

New comment by foxhop in "Llama 3.2: Revolutionizing edge AI and vision with open, customizable models"

foxhop — Wed, 25 Sep 2024 22:29:22 +0000

My guess is it uses the same vocabulary size as llama 3.1 which is 128,000 different tokens (words) to support many languages. Parameter count is less of an indicator of fitness than previously thought.