HackerTrans
トップ新着トレンドコメント過去質問紹介求人

tymscar

no profile record

投稿

Rick and Morty Tried to Warn Us About Agentic AI

jadarma.github.io
2 ポイント·投稿者 tymscar·2 か月前·0 コメント

The Things I Wanted to Know Before Buying Apple's Studio Display XDR

blog.tymscar.com
6 ポイント·投稿者 tymscar·3 か月前·0 コメント

Unified Modules for Your Nixfiles

jadarma.github.io
2 ポイント·投稿者 tymscar·4 か月前·0 コメント

How to Quiet a Ugreen 4800 Plus Without Sacrificing Drive Temps

blog.tymscar.com
2 ポイント·投稿者 tymscar·5 か月前·0 コメント

Academic Slop Just Reached a New Low

jadarma.github.io
14 ポイント·投稿者 tymscar·5 か月前·0 コメント

Automating What Backblaze Lifecycle Rules Don't Do Instantly

blog.tymscar.com
3 ポイント·投稿者 tymscar·7 か月前·0 コメント

I tried Gleam for Advent of Code

blog.tymscar.com
351 ポイント·投稿者 tymscar·7 か月前·214 コメント

Imgur geo-blocked the UK, so I geo-unblocked my network

blog.tymscar.com
494 ポイント·投稿者 tymscar·7 か月前·173 コメント

OpenAI Demo'd Fixing Issue #2472 Live. It's Still Open

blog.tymscar.com
10 ポイント·投稿者 tymscar·8 か月前·1 コメント

From 400 Mbps to 1.7 Gbps: A WiFi 7 Debugging Journey

blog.tymscar.com
173 ポイント·投稿者 tymscar·8 か月前·136 コメント

When Curl Works but IntelliJ Doesn't: The Ollama Connection Mystery

blog.tymscar.com
82 ポイント·投稿者 tymscar·9 か月前·27 コメント

コメント

tymscar
·先月·議論
This is awesome, thanks for sharing
tymscar
·先月·議論
I think its a very fair thing you have flagged!
tymscar
·先月·議論
Well it doesn’t matter because the bottleneck here is actually quite small for me. The issue is vram. If anything the bottleneck is my 4080.
tymscar
·先月·議論
Thanks!

I did get feedback on all sorts of things over the years.

One of them was to do with sentence lengths.
tymscar
·先月·議論
I would bet my trillion-dollar company on it because I understand how RAM works.
tymscar
·先月·議論
If you use NixOS, you don’t need to do any of that anymore. A single command in the CLI, and you have everything I do.
tymscar
·先月·議論
I did mention that in my case I had the 4080, but you do not need the 4080 whatsoever. You can run the same model with less context on a single £200 V100 or with the same amount of context on two of these.
tymscar
·先月·議論
Well I did in fact meaningfully combined them without an issue, that was the whole point of the blogpost.
tymscar
·先月·議論
Building computers is very easy. I would suggest watching a YouTube video to get the general gist, and then once you buy the parts, just Google for whatever doesn’t go well.

I built my first Pentium 4 one when I was like six, so I’m sure someone much older that’s into tech can do it without an issue.

There are also tons of Discord communities that are willing to help you live if you encounter any issues.
tymscar
·先月·議論
GPTzero is a joke.

It thinks this is AI: “I bought a datacenter GPU that doesn’t even have a normal PCIe connector, stuck it in my gaming PC with an adapter, and now I have 32GB of VRAM across two GPUs running a 27 billion parameter model at 32 tokens per second.”

There’s nothing AI about that. Not all SOTA LLMs agree, hell, none of them do. The same exact example I sent here gives me 0% in some, 10% in others, 100% in GPTzero.
tymscar
·先月·議論
Neither does this one. I replied in another thread. It comes out as 0% and the one from 2021 comes out as 8%. LLM detectors are all BS
tymscar
·先月·議論
I have written the blog post. I know empirically that I have used 0% AI while writing it. I also know LLM detectors are total BS and they don't really work. I have tried a couple on this exact blog post, and QuillBot, for example, gave me 0% AI detected on it.

I have then used a blog post of mine from 2021. QuillBot gave me 8%...

The King James version of the Bible came out at almost 100% AI generated a while ago. It was the HN front page.

Stop thinking that if someone writes in a way that is fun or looks like what you would think an AI writes, then it is AI generated. Loads of the time it is, but sometimes it's not, and it really hurts those like me.
tymscar
·先月·議論
I’m glad I’ve started this blog before the AI wave so I can prove people I’m just weird at writing.

It grinds my gears how so many people just talk about my writing style instead of the content.
tymscar
·先月·議論
FYI, not a single line was AI written. If there is a hallucination, it’s fully mushy brain sourced.
tymscar
·先月·議論
Agree. But I have not used AI in the slightest.

Some of us just write that. AIs had to learn it from somewhere.
tymscar
·先月·議論
AI didnt edit a single word of this post.
tymscar
·先月·議論
Not at all, no. I had this chat before about how I am one of those unlucky few that loved the way LLMs write nowadays since the mid-2000s.

Slowly but surely, I had to remove my beloved lists, emojis (though LLMs do less of that now, maybe I can incorporate them back), and emdashes.
tymscar
·先月·議論
But with miles better support, thats why I went this route. Cuda is hard to beat
tymscar
·先月·議論
Thats why I did it. I think it’s important to put things like that into perspective
tymscar
·4 か月前·議論
So it didnt end up working too well seeing that the latest data is from 4 years ago.