I put a datacenter GPU in my gaming PC

Post by tymscar » Sun, May 31, 2026, 5:53 PM UTC

jlund-molfese wrote: post #27

postalrat wrote: post #8

Earlier quoted context omitted.

Where do you think llms learned to write that way?

You can also look at past posts by the same author (before LLM usage proliferated) if you’re curious. The project is still very cool, but it’s a little less enjoyable to read when everything sounds the same. It would be just as annoying for people to manually write in a corporate/marketing style, because humanity is what makes the small web interesting. https://blog.tymscar.com/posts/privategithubcicd/

Post by mettamage » Sun, May 31, 2026, 5:57 PM UTC

Post by tymscar » Sun, May 31, 2026, 6:07 PM UTC

lelanthran wrote: post #28

postalrat wrote: post #8

Earlier quoted context omitted.

Where do you think llms learned to write that way?

> Where do you think llms learned to write that way? Not from individual human content, that's for sure - maybe MLM marketing copy? Sleazy 4AM ads? I mean, every time this response comes up, I keep asking the person to point at something written prior to 2022 that gets 80%+ on the LLM detectors, and yet no one can find anything. Maybe you, postalrat, can find something written in this style that was published prior t…

Post by iugtmkbdfil834 » Sun, May 31, 2026, 6:12 PM UTC

lukeschlather wrote: post #98

gsquaredxc wrote: post #87

Earlier quoted context omitted.

It’s not about preserving a unique writing style. When I see LLM writing my brain automatically discards the content of the writing. To me, seeing LLM writing is equivalent to going to a high-end restaurant and getting served on generic paper plates. Sure, the food looks perfectly fine and there is, in theory, nothing wrong with a paper plate. Once you see that paper plate, however, you will question how nice that es…

I skim a lot. I skimmed this article and appreciated the author documenting their process. I am indifferent to LLM or human writing for technical content. I suspect I skimmed most of the LLM parts, but judging writing quality was not why I read this post, I read it because I was curious about how useful the GPU is, and if I could replicate the author's work. Some carefully written prose wouldn't have helped me do tha…

Post by keynha » Sun, May 31, 2026, 6:16 PM UTC

mickeyp wrote: post #25

Impressive work. But the problem is not the 30 tok/s which is fine for agentic coding and chat. It's prefill; slow prefill kills agentic workloads dead. If you have 100,000 tokens at ~150tok/s per the OP, you're looking at: You have: 100000 / (150/s) You want: hms 11 min + 6.6666667 sec Which is quite a wait indeed.