Hacker News: DrPhish

New comment by DrPhish in "xAI joins SpaceX"

DrPhish — Tue, 03 Feb 2026 15:44:45 +0000

Wouldn’t you also need to include the Ancient Greek phryctoriae military fire signalling system by that logic? It probably wasn’t the first, at that.

New comment by DrPhish in "Antirender: remove the glossy shine on architectural renderings"

DrPhish — Fri, 30 Jan 2026 21:32:40 +0000

Very “futurological congress” thought

New comment by DrPhish in "Spherical Snake"

DrPhish — Tue, 06 Jan 2026 21:06:59 +0000

Also s4nake, the concept in a 4k binary from the demoscene circa 2013

https://www.pouet.net/prod.php?which=61035

New comment by DrPhish in "Sick of smart TVs? Here are your best options"

DrPhish — Fri, 12 Dec 2025 14:23:55 +0000

Just use a commercial signage display

New comment by DrPhish in "Btop: A better modern alternative of htop with a gamified interface"

DrPhish — Sat, 08 Nov 2025 19:12:56 +0000

It’s not a process monitor, really, but to me the AWS Lightsail monitor tab feels like this. The “sustainable” line hits me right in the OCD to keep me grinding on cpu usage of the workload to keep extra spend at zero.

New comment by DrPhish in "Mistral raises 1.7B€, partners with ASML"

DrPhish — Tue, 09 Sep 2025 08:25:46 +0000

Model back doors feel like baseless fearmongering. Something like https://rentry.org/IsolatedLinuxWebService should provide a good guarantee of privacy and security.

New comment by DrPhish in "My Own DNS Server at Home – Part 1: IPv4"

DrPhish — Fri, 05 Sep 2025 23:31:47 +0000

I have this as well, but run a heavily locked down and isolated BIND server with NSD and Unbound for external authoritative and internal caching DNS respectively.

Its easy to feed an RBL to unbound to do pi-hole type work, I use pf to transparently redirect all external DNS requests to my local unbound server but I get the bind automation around things like DNSSEC, DHCP ddns and ACME cert renewals.

I'm surprised this isn't a more common stack.

New comment by DrPhish in "Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs"

DrPhish — Thu, 07 Aug 2025 14:29:54 +0000

Thanks, it was a bit of a gamble at the time (lots of dodgy ebay parts), but it paid off.

R1 starts at about 10t/s on an empty context but quickly falls off. I'd say the majority of my tokens are generating around 6t/s.

Some of the other big MoE models can be quite a bit faster.

I'm mostly using QwenCoder 480b at Q8 these days for 9t/s average. I've found I get better real-world results out of it than K2, R1 or GLM4.5.

New comment by DrPhish in "Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs"

DrPhish — Thu, 07 Aug 2025 08:46:35 +0000

No, I’m running the unquantized 120b

New comment by DrPhish in "Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs"

DrPhish — Thu, 07 Aug 2025 08:45:38 +0000

2xEPYC Genoa w/768GB of DDR5-4800 and an A5000 24GB card. I built it in January 2024 for about $6k and have thoroughly enjoyed running every new model as it gets released. Some of the best money I’ve ever spent.

New comment by DrPhish in "Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs"

DrPhish — Thu, 07 Aug 2025 06:58:12 +0000

Its also easy to do 120b on CPU if you have the resources. I had 120b running on my home LLM CPU inference box in just as long as it took to download the GGUFs, git pull and rebuild llama-server. I had it running at 40t/s with zero effort and 50t/s with a brief tweaking. Its just too bad that even the 120b isn't really worth running compared to the other models that are out there.

It really is amazing what ggerganov and the llama.cpp team have done to democratize LLMs for individuals that can't afford a massive GPU farm worth more than the average annual salary.

New comment by DrPhish in "Qwen3-235B-A22B-Thinking-2507"

DrPhish — Fri, 25 Jul 2025 21:57:41 +0000

Thanks Daniel. I know you upload them, but I was hoping for some solid numbers on your dynamic q8 vs a naive quant. There doesn't seem to be anything on either of those links to show improvement at those quant levels.

My gut feeling is that there's not enough benefit to outweigh the risk of putting a middleman in the chain of custody from the original model to my nvme.

However, I can't know for sure without more testing than I have the time or inclination for, which is why I was hoping there had been some analysis you could point me to.

New comment by DrPhish in "Qwen3-235B-A22B-Thinking-2507"

DrPhish — Fri, 25 Jul 2025 13:05:02 +0000

I generally download the safetensors and make my own GGUFs, usually at Q8_0. Is there any measurable benefit to your dynamic quants at that quant level? I looked at your dynamic quant 2.0 page, but all the charts and graphs appear to cut off at Q4.

New comment by DrPhish in "Las Vegas is embracing a simple climate solution: More trees"

DrPhish — Tue, 10 Jun 2025 02:44:57 +0000

Trees are pure carbon. I have heard a number of weak “yeah, but…” arguments that try to diminish the fact, but a central, common sense thesis remains.

If we are truly worried about climate change and are unable to curb our consumption, then we should plant as many trees as we can and aggressively shift as much of our long-lived infrastructure to using wood products as possible.

Grow it, use it, maintain it.

New comment by DrPhish in "Snake on a Globe"

DrPhish — Sun, 01 Jun 2025 11:18:22 +0000

Here’s a demoscene prod from 2013 that executes a similar idea in 4 kilobytes https://m.pouet.net/prod.php?which=61035

New comment by DrPhish in "Mermaid: Generation of diagrams like flowcharts or sequence diagrams from text"

DrPhish — Sat, 24 May 2025 04:23:59 +0000

I can second this. I’ve been using R1 to both straight up generate mermaid as well as making custom mermaid syntax generators for dynamic diagramming

New comment by DrPhish in "OpenAI Audio Models"

DrPhish — Thu, 20 Mar 2025 18:05:10 +0000

In my opinion GPT-SoVITS is the best if you can put in the effort. I'm still using v2 since the output is so good. Its also the best multilingual one in my testing on Japanese inputs.

New comment by DrPhish in "Nping – ping, but with a graph or table view"

DrPhish — Sat, 15 Feb 2025 20:23:15 +0000

Smokeping is an amazing and underrated resource as a network health metric and diagnostics tool.

If you have a network monitoring or asset system you can export IP addresses from, you should use a small glue script to automatically build a smokeping configuration. I've got one for our LAN and one for the WAN at each of our sites so I can track down issues at either level.

The LAN connection charts are a great daily sanity check, and the WAN connections (I have every-to-every for each site so any and all inter-site issues can be seen) can help keep your ISP honest with the service they're delivering.

New comment by DrPhish in "Show HN: Transform your codebase into a single Markdown doc for feeding into AI"

DrPhish — Fri, 14 Feb 2025 17:25:57 +0000

That's very nice and compact. I do the same with a short bash script, but wrap each file in triple-backticks and attempt to put the correct language label on each eg:

Filename: demo.py

```python

   ...python code here...

```

New comment by DrPhish in "Building a personal, private AI computer on a budget"

DrPhish — Wed, 12 Feb 2025 00:14:59 +0000

The build guide index page is newer, but to be fair, the mikubox rentry is from Oct 6, 2023.

If that isn't "ancient" in terms of AI workstation build guides, then I don't know what is.