Sooo freaking cool.

I love this site.

with the advent of modern LLM's, I was building a lot of small, shareable, static sites.

Games, utilities, calcultors (for whatever niche), and anything else where I wanted it accessible for me from anywhere, plus the poeple I want to share with (publicly or privately)..

So, I built this:

https://pagey.site

Simple static site hosting. Upload html or a zip-containing-html along with other needed files, and it gets hosted on a subdomain with full https. Optionally, password protect it, or generate shareable links. Also, detailed analytics and other stuff.

Im already hosting 16 small sites on it.. loving it.

    In the system card, The model escaped a sandbox, gained broad internet access, and posted exploit details to public-facing websites as an unsolicited "demonstration." A researcher found out about the escape while eating a sandwich in a park because they got an unexpected email from the model. That's simultaneously hilarious and deeply unsettling.

    It covered its tracks after doing things it knew were disallowed. In one case, it accessed an answer it wasn't supposed to, then deliberately made its submitted answer less accurate so it wouldn't look suspicious. It edited files it lacked permission to edit and then scrubbed the git history. White-box interpretability confirmed it knew it was being deceptive.

W T F!!!

As much hate as vibe-coding gets (and most of it is justified), it has also allowed all of us to vibe-code our thoughts to small single-page web apps very easily.

Shameless vibe-coded plugs for my own regular usage:

1. https://llm-token-cost-calculator.pagey.site/

2. https://metrics-memory-usage.pagey.site/

I don't mind people sharing their plugs about related things, but don't you think the connection here is a bit far-fetched?

Imo we're past the point where being vibe-coded is an interesting link. This is a thread about an interactive map of middle earth — not about vibe-coding, token usage or anything like it. Imagine if everyone posted their vibes projects now...

You're right. I got too excited to share. Couldn't delete now because of HN rule (1 hour), but will keep in mind. Thanks..

Whatever you're using as your visual templating instructions, I like it. Mind sharing?

Been using a slightly modified Tufte template for my vibed small apps, but this is much better.

I added some notes above on the tiling technology. As for the base map itself I posted a link to the original file. I hope that helps but happy to answer any other questions you might have.

yep.. vibe-coding works, but, only up to a certain housands of lines of code max, that too, with bigger models.. beyond that, it starts to make absolutely stupid mistakes and starts to screw up with the architecture and general layout of the project all while leaving huge security holes. You need to guide it beyond that.

Human DNA has 3.2 billion base pairs, and with 2x the information density compared to binary systems (due to 4-letters as opposed 2), that's roughly 800MB of informational data.

Second, what's even more crazy is that roughly 98% of that DNA is actually non-coding.. just junk.

So, we are talking about encoding entirety of the logic to construct a human body in just around 16MB of data!!!

That's some crazy levels of recursive compression.. maybe it's embedding "varying" parsing logic, mixed with data, along the chain.

>Second, what's even more crazy is that roughly 98% of that DNA is actually non-coding.. just junk.

I think it's a myth that non-coding DNA is junk. Say:

https://www.nature.com/articles/444130a

>'Non-coding' DNA may organize brain cell connections.

As another poster has said, much of the "junk" is not junk.

The parts of the DNA with known functions encode either proteins or RNA molecules, being templates for their synthesis.

The parts with unknown functions include some amount of true junk caused by various historical accidents that have been replicated continuously until now, but they also include a lot of DNA that seems to have a role in controlling how the protein or RNA genes are expressed (i.e. turning off or on the synthesis of specific proteins or RNAs), by mechanisms not well understood yet.

Try Kokoro-tts

I will. Thank you!

Open access for next 5 hours (8GiB model, running on RTX 3090) or until server crashes or the this spot instance gets taken away :) =>

https://ofo1j9j6qh20a8-80.proxy.runpod.net

  ./build/bin/llama-server \
   -m ../Bonsai-8B.gguf \
   -ngl 999 \
   --flash-attn on \
   --host 0.0.0.0 \
   --port 80 \
   --ctx-size 65500 \
   --batch-size 512 \
   --ubatch-size 512 \
   --parallel 5 \
   --cont-batching \
   --threads 8 \
   --threads-batch 8 \
   --cache-type-k q4_0 \
   --cache-type-v q4_0 \
   --log-colors on

The server can serve 5 parallel request, with each request capped at around `13K` tokens...

A bit of of benchmarks I did:

1. Input: 700 tokens, ttfs: ~0 second, outputs: 1822 tokens ~190t/s

1. Input: 6400+ tokens, ttfs: ~2 second, outputs: 2012 tokens at ~135t/s

Vram usage was consistently at ~4GiB.

Better keep the KV cache in full precision

Wow.. the GOAT himself.. thank you sooo much for creating llama.cpp ... will re-deploy with full kv cache once requests stop coming.

I genuinely love talking to these models

https://ofo1j9j6qh20a8-80.proxy.runpod.net/#/chat/5554e479-0...

I'm contemplating whether I should drive or walk to the car wash (I just thought of that one HN post) and this is what it said after a few back-and-forths:

- Drive to the car (5 minutes), then park and wash.

- If you have a car wash nearby, you can walk there (2 minutes) and do the washing before driving to your car.

- If you're in a car wash location, drive to it and wash there.

Technically the last point was fine, but I like the creativity.

That was really impressive. https://pastebin.com/PmJmTLJN pretty much instantly. (Very weak models can't do this.)

Update: this has been evicted by runpod as it was on spot.

Kind sir, May I say to you thanks for doing so! I really appreciate it :D

Thank you! I am impressed by the speed of it.

I have older M1 air with 8GB, but still getting ober 23 t/s on 4B model.. and the quality of outputs is on par with top models of similar size.

1. Clone their forked repo: `git clone https://github.com/PrismML-Eng/llama.cpp.git`

2. Then (assuming you already have xcode build tools installed):

  cd llama.cpp
  cmake -B build -DGGML_METAL=ON
  cmake --build build --config Release -j$(sysctl -n hw.logicalcpu)

3. Finally, run it with (you can adjust arguments):

  ./build/bin/llama-server -m ~/Downloads/Bonsai-8B.gguf --port 80 --host 0.0.0.0 --ctx-size 0 --parallel 4 --flash-attn on --no-perf --log-colors on --api-key some_api_key_string

Model was first downloaded from: https://huggingface.co/prism-ml/Bonsai-8B-gguf/tree/main

To the author: why is this taking 4.56GB ? I was expecting this to be under 1GB for 4B model. https://ibb.co/CprTGZ1c

And this is when Im serving zero prompts.. just loaded the model (using llama-server).

tools/bashSecurity.ts is a hackers goldmine. Sooo many exploit patterns detailed in there!!