Hacker News: Zetaphor

New comment by Zetaphor in "Wall Street is growing skeptical of the data center boom"

Zetaphor — Tue, 22 Sep 2026 04:21:15 +0000

Every day I am grateful that I only paid $1800

New comment by Zetaphor in "Wall Street is growing skeptical of the data center boom"

Zetaphor — Mon, 21 Sep 2026 21:45:58 +0000

Different people have different requirements. I use my local model for coding regularly. It doesn't help the conversation that things like quant, config, harness, and even prompting are equally as important to your outcomes as the choice of model.

New comment by Zetaphor in "Wall Street is growing skeptical of the data center boom"

Zetaphor — Mon, 21 Sep 2026 21:22:06 +0000

Asked my agent to dump this to pastebin from my phone since I won't be home for a while

https://pastebin.com/bBXbpDyu

Here's the chat template I use:

https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates

New comment by Zetaphor in "Wall Street Is Growing Skeptical of the Data Center Boom"

Zetaphor — Mon, 21 Sep 2026 20:56:58 +0000

Smaller models have improved in every regard, not just domain specific challenges. You can see this in the benchmarks or by just testing one yourself side by side with an older release.

I'm using it at work in multiple data classification and redaction pipelines. It's replaced tedious manual labor and opened that staff up to focus on the parts of the work that requires their human intuition, rather than spending time on tedium.

Presumably part of the reason you don't get a response is your hostile approach to asking.

New comment by Zetaphor in "Wall Street is growing skeptical of the data center boom"

Zetaphor — Mon, 21 Sep 2026 20:23:48 +0000

Well said, they're competing on marketing rather than merit. Everyone defaults to the frontier instead of exploring more optimal options

New comment by Zetaphor in "Wall Street is growing skeptical of the data center boom"

Zetaphor — Mon, 21 Sep 2026 20:22:50 +0000

Open models keep getting bigger, but smaller open models also keep getting smarter. What I can do with an 8b used to require a 32b.

Also the decision makers who are signing off on things like ChatGPT Enterprise are at least 18 months behind the curve of what you can actually do with these things and how cheap they can be. They're still trying to figure out how to actually adopt the tech out of a sense of fomo, nevermind making nuanced decisions about hosting an open weights model. I see this firsthand in my own job.

I'm talking about adding facts to a model by modifying engrams or trying to bolster guardrails with J-washing, meanwhile they're still trying to figure out how to best prompt Copilot.

Give it a few years for everyone else to catch up, I'm barely able to catch my breath before there's some new development in the open source/weights space

New comment by Zetaphor in "Wall Street Is Growing Skeptical of the Data Center Boom"

Zetaphor — Mon, 21 Sep 2026 20:15:35 +0000

What does Omarchy or Spotify have to do with anything I just said?

I am a software engineer, and using this software in my personal and professional work has lead me to a very different conclusion, but everyone is entitled to their opinion.

New comment by Zetaphor in "Wall Street Is Growing Skeptical of the Data Center Boom"

Zetaphor — Mon, 21 Sep 2026 20:04:45 +0000

You don't need a data center to get real work done. Not every task requires "PhD level intelligence"

New comment by Zetaphor in "Wall Street is growing skeptical of the data center boom"

Zetaphor — Mon, 21 Sep 2026 19:58:38 +0000

I have a shoebox sized computer (Framework Desktop) running Qwen 3.8 Flash Next. It has completely replaced my use of proprietary models in my personal life. 6 months ago I would have told you this was impossible. Based on the current trajectory I expect 6 months from now I'll have a Mythos class model at home. The best part is not having to concern myself with token cost has unlocked all kinds of experimentation and use cases. I have been pushing over a billion tokens per week for multiple weeks now, all for the $52/year it costs to keep this machine running 24/7

New comment by Zetaphor in "Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint"

Zetaphor — Fri, 18 Sep 2026 03:01:07 +0000

I always just throw an agent at it. Is this the RSI I keep hearing about

New comment by Zetaphor in "Show HN: Sunk Cost – How long until a local LLM rig pays for itself?"

Zetaphor — Tue, 15 Sep 2026 03:01:07 +0000

This tells me that the max throughput for the models I'm running on my hardware is lower than it actually is. Please allow us to tweak all the variables instead of locking me in to whatever rate you found by searching

New comment by Zetaphor in "Nitter has more working instances than before the takedowns"

Zetaphor — Sat, 05 Sep 2026 17:21:01 +0000

dang and team tread carefully but carry a big stick

New comment by Zetaphor in "Mamdani bans AI in NYC schools"

Zetaphor — Wed, 02 Sep 2026 22:37:49 +0000

Saying that a human teacher is equivalent to an LLM is derogatory to the teachers and exaggerating the capabilities of the LLM. I say this as someone who uses these things daily in my work and personal life. Let's not murky the waters with complete falsehoods

New comment by Zetaphor in "How accurate have Ed Zitron's AI skeptic predictions been?"

Zetaphor — Wed, 02 Sep 2026 05:07:07 +0000

They're the ones who are dying. Gen Z grew up on the cloud

New comment by Zetaphor in "Sonic Pi"

Zetaphor — Wed, 02 Sep 2026 01:16:15 +0000

Hard in what way? Just install the Flatpak?

https://flathub.org/en/apps/net.sonic_pi.SonicPi

New comment by Zetaphor in "TrueForge – The open-source agent harness"

Zetaphor — Thu, 20 Aug 2026 19:56:11 +0000

Especially Pi, that's kind of the gold standard for open harnesses

New comment by Zetaphor in "Watching TikTok and Instagram deactivates the cognitive control network: Study"

Zetaphor — Thu, 20 Aug 2026 19:19:15 +0000

It's this generations leaded gasoline and paint

New comment by Zetaphor in "Qwen3.8-2.4T"

Zetaphor — Thu, 13 Aug 2026 04:52:49 +0000

Unfortunately they're currently too busy trying to patent tool calling

https://news.ycombinator.com/item?id=49243397

New comment by Zetaphor in "DeepSeek V4 Pro 0813"

Zetaphor — Wed, 12 Aug 2026 18:26:40 +0000

It's the third link on the front page right now?

New comment by Zetaphor in "llama.cpp"

Zetaphor — Wed, 12 Aug 2026 13:46:13 +0000

I'm running on Strix Halo so memory bandwidth is my constraint. In that example I'm describing the choice between using ROCm or Vulkan. I have a llama-swap config that can call different instances of llama-server running a toolbox with either runtime.