Hacker News: Hedepig

New comment by Hedepig in "Anthropic acquires Bun"

Hedepig — Wed, 03 Dec 2025 08:13:15 +0000

... and Oracle lost

New comment by Hedepig in "Cloudflare Global Network experiencing issues"

Hedepig — Tue, 18 Nov 2025 11:51:08 +0000

Except on HN

HAHA!

Our servers are still down, though

New comment by Hedepig in "Ask HN: Work on robotics or agents?"

Hedepig — Fri, 10 Jan 2025 06:55:33 +0000

I mean, this could be phase 2 of career growth. Focus on personal growth first by surrounding by experts.

New comment by Hedepig in "Show HN: Llama 3.2 Interpretability with Sparse Autoencoders"

Hedepig — Sat, 23 Nov 2024 14:46:25 +0000

The static nature of LLMs is a compelling argument against the reasoning ability.

But, it can learn, albeit in a limited way, using the context. Though to my knowledge that doesn't scale well.

New comment by Hedepig in "Show HN: Llama 3.2 Interpretability with Sparse Autoencoders"

Hedepig — Sat, 23 Nov 2024 11:27:01 +0000

I do see your point, and it is a good point.

My observation is that the models are better at evaluating than they are generating, this is the technique used in the o1 models. They will use unaligned hidden tokens as "thinking" steps that will include evaluation of previous attempts.

I thought that was a good approach to vetting bad ideas.

New comment by Hedepig in "Show HN: Llama 3.2 Interpretability with Sparse Autoencoders"

Hedepig — Sat, 23 Nov 2024 07:34:42 +0000

If we do figure out how to vet these thoughts, would you call it reasoning?

New comment by Hedepig in "Show HN: Llama 3.2 Interpretability with Sparse Autoencoders"

Hedepig — Fri, 22 Nov 2024 18:16:10 +0000

> then it is a correct formula to say 'it's not "true reasoning"'

why is that point fundamental?

New comment by Hedepig in "Show HN: Llama 3.2 Interpretability with Sparse Autoencoders"

Hedepig — Fri, 22 Nov 2024 08:12:47 +0000

This is not totally my experience, I've debated a successful engineer who by all accounts has good reasoning skills, but he will absolutely double down on unreasonable ideas he's made on the fly he if can find what he considers a coherent argument behind them. Sometimes if I absolutely can prove him wrong he'll change his mind.

But I think this is ego getting in the way, and our reluctance to change our minds.

We like to point to artificial intelligence and explain how it works differently and then say therefore it's not "true reasoning". I'm not sure that's a good conclusion. We should look at the output and decide. As flawed as it is, I think it's rather impressive

New comment by Hedepig in "Garak, LLM Vulnerability Scanner"

Hedepig — Mon, 18 Nov 2024 08:05:13 +0000

I read the original comment as hyperbole. But can see why it was confusing.

Edit: that came out way more condescending than I intentended

New comment by Hedepig in "How I write code using Cursor"

Hedepig — Tue, 29 Oct 2024 07:17:11 +0000

Have you had a go with the o1 range of models?

New comment by Hedepig in "Root cause of Alzheimer's may be fat buildup in brain cells, research suggests"

Hedepig — Wed, 20 Mar 2024 07:31:14 +0000

I think you're right

The danger is two fold

1. People don't eat fatty foods which have solid evidence for their benefits (e.g. Virgin olive oil)

2. People substitute the lack of fats with sugar, which I believe (not an expert) has a lot literature linking it with obesity

New comment by Hedepig in "Vesuvius Challenge 2023 Grand Prize awarded: we can read the first scroll"

Hedepig — Tue, 06 Feb 2024 10:17:22 +0000

Argh, what has Black Mirror done to our sense of optimism?

(I agree with you).

New comment by Hedepig in "Thomas Cochrane"

Hedepig — Tue, 02 Jan 2024 22:23:15 +0000

I mentioned in another comment, I enjoyed the structure and found it much easier to process. This is despite mostly reading long form articles and never having been a huge twitter user.

New comment by Hedepig in "Thomas Cochrane"

Hedepig — Tue, 02 Jan 2024 22:21:20 +0000

On the contrary, I have never been a heavy twitter user, yet I would dearly love all articles I read to be broken down like this. I definitely find it easier to process a list structure like this.

New comment by Hedepig in "VideoPoet A large language model for zero-shot video generation"

Hedepig — Tue, 19 Dec 2023 23:33:01 +0000

For now

New comment by Hedepig in "Magicoder: Source Code Is All You Need"

Hedepig — Wed, 06 Dec 2023 06:51:35 +0000

> tends to give subjectively better responses to "bad prompts".

I wonder if a first pass with another model to expand these so called bad prompts into better prompts would work.

New comment by Hedepig in "Llamafile lets you distribute and run LLMs with a single file"

Hedepig — Thu, 30 Nov 2023 17:48:49 +0000

Thank you for this :)

New comment by Hedepig in "Llamafile lets you distribute and run LLMs with a single file"

Hedepig — Wed, 29 Nov 2023 21:51:13 +0000

I am currently tinkering with this all, you can download a 3b parameter model and run it on your phone. Of course it isn't that great, but I had a 3b param model[1] on my potato computer (a mid ryzen cpu with onboard graphics) that does surprisingly well on benchmarks and my experience has been pretty good with it.

Of course, more interesting things happen when you get to 32b and the 70b param models, which will require high end chips like 3090s.

[1] https://huggingface.co/TheBloke/rocket-3B-GGUF

New comment by Hedepig in "Why aren't motherboards mostly USB-C by now? (2021)"

Hedepig — Sun, 19 Nov 2023 10:55:08 +0000

At the risk of sounding a bit dumb, I shorted my motherboard with a USB A, it felt like I got it right, and pushed it in, at which point it shutdown. Fortunately there didn't seem to be any permanent damage

New comment by Hedepig in "The first stable release of a memory safe sudo implementation"

Hedepig — Mon, 06 Nov 2023 18:42:17 +0000

Does it not provide some protection against a buffer overflow?