HackerLangs
TopNewTrendsCommentsPastAskShowJobs

krapht

1,696 karmajoined قبل 15 سنة

comments

krapht
·قبل 18 يومًا·discuss
> The catch is that for image resolutions >=700x700pixels (most production usecases)

Citation needed? 2XL looks like you go up to 800x800 pixel inputs. This isn't the dealbreaker you say it is - all pipelines benefit from thoughtful crop and rescaling before going to inference.
krapht
·قبل 24 يومًا·discuss
More than just your commute. Any downtime where you are doing a mindless chore is prime podcast time.
krapht
·الشهر الماضي·discuss
I've heard of people using anythingllm for this purpose.

Basic rag is almost stupid in how easy it is, though. You grep for keywords, take the surrounding paragraph, then stuff it all into your llm prompt.

The next upgrade is to automate keyword extraction by putting your documents into a vector store and search by vector similarity.
krapht
·الشهر الماضي·discuss
Don't post generated comments or AI-edited comments. HN is for conversation between humans. https://news.ycombinator.com/newsguidelines.html#generated
krapht
·قبل شهرين·discuss
I went and looked at the code. It's AI bots and a few confused trend followers all the way down. There's no way anything in there works.
krapht
·قبل شهرين·discuss
<article excerpt>

What AI actually does Mutinex has built what it describes as a “multi-agent system,” where each agent acts as a domain specialist. For example, one agent understands marketing econometrics, another understands competitive pricing theory, another diagnoses model failures.

By combining Tracer, which cleans and makes sense of Hershey’s data infrastructure, with Mutinex’s AI system, Hershey is now able run models in as little as three weeks.

In practice, that means faster iteration on how marketing spend is evaluated and adjusted, rather than waiting for lagging historical reads.

“Most companies don’t have an AI problem. They have a data readiness problem,” said Sarah Martinez, chief commercial officer, Tracer.

</article excerpt>

Instead of the headline, it sounds like they've hired an external company to clean up their ETL pipelines. That seems useful.

I'm going to doubt spooling up <massive LLM> with <appropriate system prompt> is going to be the thing that reduces their analysis time.
krapht
·قبل شهرين·discuss
You can go your entire career without recursing, or using a tree data structure in its raw form (i.e. you only use it as part of a library)
krapht
·قبل 3 أشهر·discuss
which city is that? I want to move there with my children.

If you desperately want mediocre chromebook instruction for your children; where your classmates turn in ChatGPT essays as original work, feel free to move to Virginia.
krapht
·قبل 4 أشهر·discuss
Lots of sensors these days will give you 10 or 12 bits of data per color channel. You may want ordered dithering when previewing on an 8 bit display.
krapht
·قبل 4 أشهر·discuss
Is the code actually good though? Not seeing any benchmarks vs numexpr, numba, or Jax
krapht
·قبل 4 أشهر·discuss
Sublime Text? Sure, doesn't have the long tail of extensions, but surely most people don't need those. The biggest issue with ST being the fact that it costs money...
krapht
·قبل 4 أشهر·discuss
Paying customers use docker desktop.
krapht
·قبل 4 أشهر·discuss
Even if you don't like the current administration, the rank and file are still out there doing valuable work. The government is more than ICE; it also administers welfare, funds research, collects taxes, and distributes social security payments to the old and infirm.
krapht
·قبل 4 أشهر·discuss
So? If the goal was to attract corporations you'd release under a BSD license.
krapht
·قبل 4 أشهر·discuss
Why? Is Scotland innocent?
krapht
·قبل 5 أشهر·discuss
This post makes me sad for two reasons:

1) kids k-5 are using laptops 2) websites are so bloated today that browsing on a Chromebook is causing agitation

Otherwise I don't have anything topical for this post, but good luck OP
krapht
·قبل 5 أشهر·discuss
Yes, but is this a problem? Haven't most betting markets turned out to offer accurate predictions?
krapht
·قبل 5 أشهر·discuss
The human is responsible. How is this a question? You are responsible for any machines or animals that work on your behalf, since they themselves can't be legally culpable.

No, an oversized markov chain is not in any way a human being.
krapht
·قبل 5 أشهر·discuss
Why not have a megatopic for things that don't need their own topic?

Topics are necessary when you start having a huge Zulip server, 100+ people. There's so much noise --- dividing things by channel is too coarse.

I participate in several open source Zulip servers and it reminds me of a better IRC. It's a lot more ergonomic that Gitter or Discord.
krapht
·قبل 5 أشهر·discuss
I've seen some small firms crash and burn too, though. The problem is small firms are easy-come, easy-go; they don't have enough reputation at stake. Not sure what a good solution is.