Hacker News: ipunchghosts

New comment by ipunchghosts in "Show HN: I replaced Google Analytics with my own tool – no cookies, <1KB script"

ipunchghosts — Wed, 08 Apr 2026 00:06:36 +0000

Umami is free for me.

New comment by ipunchghosts in "Show HN: I replaced Google Analytics with my own tool – no cookies, <1KB script"

ipunchghosts — Mon, 06 Apr 2026 19:01:19 +0000

How is this different from umami?

New comment by ipunchghosts in "Vermin Supreme: When I'm President Everyone Gets a Free Pony [video]"

ipunchghosts — Sat, 04 Apr 2026 01:05:31 +0000

Have an upvote for my man

New comment by ipunchghosts in "Pyodide: a Python distribution based on WebAssembly"

ipunchghosts — Tue, 17 Mar 2026 14:25:22 +0000

REMUS RLF reader runs pyodide to parse underwater drone mission files in the browser

https://isaacgerg.github.io/remus-rlf-reader/webapp/

New comment by ipunchghosts in "Can I run AI locally?"

ipunchghosts — Fri, 13 Mar 2026 19:41:00 +0000

What is S? Also, NVIDIA RTX 4500 Ada is missing.

New comment by ipunchghosts in "Autoresearch: Agents researching on single-GPU nanochat training automatically"

ipunchghosts — Sun, 08 Mar 2026 14:22:28 +0000

Goedel machine.

New comment by ipunchghosts in "Dario Amodei calls OpenAI’s messaging around military deal ‘straight up lies’"

ipunchghosts — Thu, 05 Mar 2026 15:16:44 +0000

> but there's a massive financial reality here.

Not a chance. The DoD has massive pockers which and INCREDIBLY SPREAD OUT. You can't underestimate how spread this money is. The DoD has maybe a 64 GPU cluster and ALMOST NO ONE USES IT FOR DEEP MODEL TRAINING. Even contractors end up working with DGX boxes to do all their training.

As of 2023, I was doing the largest Deep learning training runs out of anyone I have known in the industry and I've been in the industry for 20 yeras. The second best groups behind mine were using 4 GPU locally machines that they had to purchase on contract.

There's no way the DoD can train these models themselves, not even close. They are COMPLETELY DEPENDENT ON INDUSTRY. I was the PM for a DARPA program in 2023 and SAME PROBLEM. They had no compute or would rely on university compute if a program had a university partner. YOU HAVE NO IDEA HOW FAR BEHIND THE DOD IS IN THIS SPACE.

New comment by ipunchghosts in "30 Years of ReactOS"

ipunchghosts — Thu, 22 Jan 2026 14:18:49 +0000

I would think claude code would help make a quick dent in boosting reactos capabilities. Curious what others think.

New comment by ipunchghosts in "Ask HN: How can I get better at using AI for programming?"

ipunchghosts — Sat, 13 Dec 2025 18:12:57 +0000

Ask people to do things for you. Then you will learn how to work with something/someone who has faults but can overall be useful if you know how to view the interaction.

New comment by ipunchghosts in "François Chollet: The Arc Prize and How We Get to AGI [video]"

ipunchghosts — Mon, 07 Jul 2025 20:37:58 +0000

I agree strongly with this take but find it hard to convince others of it. Instead, people keep thinking there is a magic bullet to discover resulting in a lot of wasted resources and money.

New comment by ipunchghosts in "When memory was measured in kilobytes: The art of efficient vision"

ipunchghosts — Thu, 05 Jun 2025 15:41:19 +0000

Kasturi was my undergraduate honors advisor!

New comment by ipunchghosts in "New sonar tool is a 'game changer' for mapping the sea floor"

ipunchghosts — Mon, 02 Jun 2025 17:40:39 +0000

There's papers on this. Google AirSAS.

Been on sas biz for 12 years, resolution is much better than multibeam at range.

New sonar tool is a 'game changer' for mapping the sea floor

ipunchghosts — Mon, 02 Jun 2025 01:18:26 +0000

Article URL: https://www.science.org/content/article/new-sonar-tool-game-changer-mapping-sea-floor

Comments URL: https://news.ycombinator.com/item?id=44155073

Points: 6

# Comments: 2

New comment by ipunchghosts in "Triangle splatting: radiance fields represented by triangles"

ipunchghosts — Sat, 31 May 2025 15:26:18 +0000

Autoencoders should output these kinds of splats instead of pixel outputs and likely obtain better representations of the world at the bottleneck. These features can be used for downstream tasks.

New comment by ipunchghosts in "The Fractured Entangled Representation Hypothesis"

ipunchghosts — Tue, 20 May 2025 18:52:48 +0000

I think we are saying the same thing. Please correct me though where I am wrong. You could look at the maps in some way but instead of the basis being one hot dimensions (the standard basis), it could be rotated.

New comment by ipunchghosts in "The Fractured Entangled Representation Hypothesis"

ipunchghosts — Tue, 20 May 2025 18:45:30 +0000

I am interested in doing research like this. Is there any way I can be a part of it or a similar group? I have been fighting for funding from DoD for many years but to no avail so I largely have to do this research on my own time or solve my current grant's problems so that i can work on this. In my mind, this kind of research is the most interesting and important right now in the deep learning field. I am a hard worker and a high-throughput thinking... how can i get connected to otherwise with a similar mindset?

New comment by ipunchghosts in "The Fractured Entangled Representation Hypothesis"

ipunchghosts — Tue, 20 May 2025 18:42:41 +0000

I am glad they evaluated this hypothesis using weight decay which is primarily thought of to induce a structured representation. My first thought was that the entire paper was useless if they didn't do this experiment.

I find it rather interesting that the structured representations go from sparse to full to sparse as a function of layer depth. I have noticed that applying weight decay penalty as an exponential function of layer depth gives improved results over using a global weight decay.

New comment by ipunchghosts in "The Fractured Entangled Representation Hypothesis"

ipunchghosts — Tue, 20 May 2025 18:40:48 +0000

Is what your saying imply that there is a rotation matrix you can apply to each activation output to make it less entangled?

New comment by ipunchghosts in "Adventures in Imbalanced Learning and Class Weight"

ipunchghosts — Sat, 10 May 2025 22:09:52 +0000

I read the article and the take away is that class weights and stratified sampling did not help for the OPs problem.

New comment by ipunchghosts in "My new deadline: 20 years to give away virtually all my wealth"

ipunchghosts — Fri, 09 May 2025 00:56:45 +0000

AI as defined today is brittle. I am interested in understanding the fundamentals of learning so that systems can be learn as quickly as humans and have thier same level of robustness. Such a breakthrough would have a worldwide impact.

As far as I can tell, very few places are looking into this topic area. Jeff Hawkins group is one of the few places. I would like to get involved as this area is my passion but I can't connected to funding to do so.