HackerTrans
TopNewTrendsCommentsPastAskShowJobs

rain1

1,127 karmajoined 8 ปีที่แล้ว

Submissions

CleoBench: Can Fable mathematically prove Cleo's integrals?

rain-1.github.io
2 points·by rain1·5 วันที่ผ่านมา·0 comments

Transformer Architecture Visualizer

weavers.neocities.org
2 points·by rain1·7 เดือนที่ผ่านมา·1 comments

How large are large language models?

gist.github.com
263 points·by rain1·ปีที่แล้ว·150 comments

Midjourney Generating Screenshots of Movies

unrollnow.com
2 points·by rain1·2 ปีที่แล้ว·0 comments

Fixing the volume on my Bluetooth earbuds

blog.ornx.net
293 points·by rain1·3 ปีที่แล้ว·85 comments

Crossword Solving with GPT

gist.github.com
2 points·by rain1·3 ปีที่แล้ว·0 comments

Run Llama 13B with a 6GB graphics card

gist.github.com
618 points·by rain1·3 ปีที่แล้ว·266 comments

AI Scientists: Safe and Useful AI?

yoshuabengio.org
2 points·by rain1·3 ปีที่แล้ว·0 comments

TEDx – Eliezer Yudkowsky – Unleashing the Power of Artificial Intelligence

youtube.com
2 points·by rain1·3 ปีที่แล้ว·3 comments

Does prompt injection matter to AutoGPT?

gist.github.com
1 points·by rain1·3 ปีที่แล้ว·0 comments

Pair Programming Experience with Bard

gist.github.com
2 points·by rain1·3 ปีที่แล้ว·0 comments

WorLLMs

gist.github.com
2 points·by rain1·3 ปีที่แล้ว·0 comments

[untitled]

1 points·by rain1·3 ปีที่แล้ว·0 comments

[untitled]

11 points·by rain1·3 ปีที่แล้ว·0 comments

Eliezer Yudkowsky's Letter in Time Magazine

thezvi.substack.com
4 points·by rain1·3 ปีที่แล้ว·0 comments

Probing Compositional Understanding of ChatGPT with SVG

evanthebouncy.medium.com
3 points·by rain1·3 ปีที่แล้ว·2 comments

Blame Me for Trying

unremediatedgender.space
2 points·by rain1·3 ปีที่แล้ว·0 comments

Is it time for a pause? By Kelsey Piper

planned-obsolescence.org
2 points·by rain1·3 ปีที่แล้ว·1 comments

LLMs and GPT: Some of my favorite learning materials

gist.github.com
280 points·by rain1·3 ปีที่แล้ว·24 comments

Show HN: GPT-4 Reverse Turing Test

gist.github.com
288 points·by rain1·3 ปีที่แล้ว·272 comments

comments

rain1
·7 เดือนที่ผ่านมา·discuss
I've used Google Antigravity to write scripts to download and produce architecture diagrams for various LLMs from huggingface. It's pretty useful so I thought I'd share it.

There's also a model comparison spreadsheet that you can compare sizes and such https://weavers.neocities.org/architecture-encyclopedia/mode...

If you'd like any additional models to be added I can add them in.
rain1
·ปีที่แล้ว·discuss
The Gemma models are too small to be included in this list.

You're right the T5 stuff is very important historically but they're below 11B and I don't have much to say about them. Definitely a very interesting and important set of models though.
rain1
·ปีที่แล้ว·discuss
Yes but just purely in terms of entropy, you can't make a model better than GPT-4 by training it on GPT-4 outputs. The limit you would converge towards is GPT-4.
rain1
·ปีที่แล้ว·discuss
This is kind of related to the jack morris post https://blog.jxmo.io/p/there-are-no-new-ideas-in-ai-only he discusses how the big leaps in LLMs have mostly come - not so much from new training methods or arch. changes as such - but the ability of new archs. to ingest more data.
rain1
·ปีที่แล้ว·discuss
It's extremely interesting how powerful a language model is at compression.

When you train it to be an assistant model, it's better at compressing assistant transcripts than it is general text.

There is an eval which I have a lot of interested in and respect for https://huggingface.co/spaces/Jellyfish042/UncheatableEval called UncheatableEval, which tests how good of a language model an LLM is by applying it on a range of compression tasks.

This task is essentially impossible to 'cheat'. Compression is a benchmark you cannot game!
rain1
·ปีที่แล้ว·discuss
I think that one thing that this chart makes visually very clear is the point I about GPT-3 being such a huge leap, and there being a long gap before anybody was able to match it.
rain1
·ปีที่แล้ว·discuss
This is really awesome. Thank you for creating that. I included a screenshot and link to the chart with credit to you in a comment to my post.
rain1
·ปีที่แล้ว·discuss
I can correct mistakes.

> it somehow merged Llama 4 Maverick's custom Arena chatbot version with Behemoth

I can clarify this part. I wrote 'There was a scandal as facebook decided to mislead people by gaming the lmarena benchmark site - they served one version of llama-4 there and released a different model' which is true.

But it is inside the section about the llama 4 model behemoth. So I see how that could be confusing/misleading.

I could restructure that section a little to improve it.

> Llama 405B was also trained on more than 15 trillion tokens[1],

You're talking about Llama 405B instruct, I'm talking about Llama 405B base. Of course the instruct model has been traiend on more tokens.

> why is there such a focus on token training count?

I tried to include the rough training token count for each model I wrote about - plus additional details about training data mixture if available. Training data is an important part of an LLM.
rain1
·ปีที่แล้ว·discuss
I have corrected that. It was supposed to say "None of this document was written by AI."

Thank you for spotting the error.
rain1
·2 ปีที่แล้ว·discuss
> Take care of your mental health

How?
rain1
·2 ปีที่แล้ว·discuss
todsacerdoti is a spambot btw
rain1
·3 ปีที่แล้ว·discuss
I don't understand this. Please can you point me to information about it?
rain1
·3 ปีที่แล้ว·discuss
The people that are astonished by this just need to learn why.

It's not the function that is wrong, it's those people.
rain1
·3 ปีที่แล้ว·discuss
This is incorrect, the goats and car are behind doors. They are not inside cardboard boxes.
rain1
·3 ปีที่แล้ว·discuss
This is an example of hallucination.

An LLM doesn't know anything about itself - it can be pre-prompted with facts about itself, but this is going to be an example of it just making plausible text up.
rain1
·3 ปีที่แล้ว·discuss
tell me you're posting from an armchair without telling me you're posting from an armchair
rain1
·3 ปีที่แล้ว·discuss
what the actual fuck were they thinking uploading dolphin to steam??
rain1
·3 ปีที่แล้ว·discuss
Why don't they let us edit what the bot says? Could be useful.
rain1
·3 ปีที่แล้ว·discuss
This is the future of linux syscalls. Get on board with this or get left behind.
rain1
·3 ปีที่แล้ว·discuss
so list a few known to work models and their requirements