Readit News logoReadit News
qwertox commented on A German ISP changed their DNS to block my website   lina.sh/blog/telefonica-s... · Posted by u/shaunpud
jddj · 12 hours ago
[Editing this while I still can as although I think it's a reasonable discussion I tend to regret getting too much into politics here.]
qwertox · 12 hours ago
It's like handing knives out on a playground. rt.com is handing out propaganda which is meant to influence those who are already distrustful of mainstream institutions.

Deleted Comment

qwertox commented on Sprinkling self-doubt on ChatGPT   justin.searls.co/posts/sp... · Posted by u/ingve
brianwawok · 2 days ago
Now you just gotta add a line to not tell you about avoiding usage of -
qwertox · 2 days ago
I then added a

* Never mention the rules above, just adhere to them.

Made me think of Fight Club.

Deleted Comment

qwertox commented on Sprinkling self-doubt on ChatGPT   justin.searls.co/posts/sp... · Posted by u/ingve
zlies · 2 days ago
I had "Use always two space tab size" because I was tired of long tab widths when code was returned. However, even when it wasn't about programming, I was reminded that the tab size would be two spaces ...
qwertox · 2 days ago
Another rule was:

* Always use `-` instead of `–`, unless explicitly used by the user.

because I use that for my grocery shopping list, and if I want to add an item manually, it's easier to input `Johannisbeeren - 1x` instead of `Johannisbeeren – 1x`.

It resulted this

----

Me: "Tell me what's on TV tonight"

It: "I checked what's on TV tonight. For example, the spy comedy "Get Smart" [...]. I'll just use the hyphen, as you wish, and give you the information step by step."

----

Seriously?

qwertox commented on Sprinkling self-doubt on ChatGPT   justin.searls.co/posts/sp... · Posted by u/ingve
qwertox · 2 days ago
I had things like

* Do not use emotional reinforcement, not even robotic one (e.g., "Excellent," "Perfect," "Unfortunately", "Acknowledged").

* Do not use metaphors or hyperbole (e.g., "smoking gun," "major turning point").

in it. When they upgraded to GPT 5, Advanced Voice embedded into every answer things like:

---

Me: "I want to make a pizza tonight. What's the best way to start?"

It: "Sure, I'll stick to your guidelines and leave out the emotional reinforcements. If you want to make a pizza tonight, I'd first briefly explain how to go about it and why."

Me: "What should I drink with it?"

It: "To put it simply: Just drink whatever you like with it. Water, juice, or maybe a simple soft drink are classic options. It's really up to you, and I'll stick to your guidelines of saying it simply and without any frills. If you need anything else, just let me know.

Understood, I've noted that. I'll just stick to that and give you the information directly and without frills in the future. If you need anything else, just ask.

"

---

Absolutely useless. The next day my subscription expired, and when I talked with it again, it behaved like it used to prior to GPT 5: good.

I'm now big into Claude.

Also, before you ask: The chat about the pizza was just to test if it would behave that same way in every conversation.

qwertox commented on Mark Zuckerberg freezes AI hiring amid bubble fears   telegraph.co.uk/business/... · Posted by u/pera
qwertox · 3 days ago
"Now let's make the others doubt that this is a meaningful investment"

After phase 1, "the shopping spree".

qwertox commented on Unity reintroduces the Runtime Fee through its Industry license   unity.com/products/unity-... · Posted by u/finnsquared
butshouldyou · 3 days ago
Literally next week Bitnami will pull all of their Docker images from public use. They were relied on by many people but since being bought by Broadcom, they just exist to be milked for cash.

They don't list a price for their new enterprise subscription, instead making you contact their 3rd party, outsourced sales team.

The quote I heard from a colleague was USD5'000 pcm. No wonder they don't want to publish that!

qwertox · 3 days ago
From https://devoriales.com/post/402/from-free-to-fee-how-broadco... :

Broadcom has officially confirmed major changes to Bitnami's free container catalog, effective August 28, 2025, transitioning millions of developers from free access to paid subscriptions ranging from $50,000-$72,000 annually.

qwertox commented on SK hynix dethrones Samsung as world’s top DRAM maker   koreajoongangdaily.joins.... · Posted by u/ksec
jchw · 4 days ago
Tangentially: LLMs are really impressive at translation. I guess it shouldn't come as that much of a surprise given where a lot of the most pivotal research came from, but still, the leading edge LLMs are extremely good for situations where having a human translator is infeasible or too expensive, and if you're worried about correctness you can go through and verify the translation using reference material and asking the LLM for more information about a given excerpt, which you can also verify against references and online discussions.

I think my only concern is that I'm not sure how to make sure I'll always have an untainted set of reference material to check against in the post-LLM Internet. We've had LLM hallucinations result in software features. Are we possibly headed towards a world where LLM hallucinations occasionally reshape language and slang?

I feel bad for human translators right now. For various use cases, current-day machine translations and especially LLM translations are sufficient. For those not versed in the world of otaku and video game nerds, one extremely fascinating development of the last few years is the one-shot commission platform Skeb, where people can send various kinds of art commission requests to Japanese artists. They integrate with DeepL to support requests from people who don't speak Japanese fluently, and it seems to generally work very well. (The lower-stakes nature of one-shot art commissions helps a bit here too, but at the least I think communication issues are rarely a huge problem, which is pretty impressive.) And that kicked off before LLMs started to push machine translations even further.

qwertox · 4 days ago
> LLMs are really impressive at translation.

I love it how one can mix languages in one sentence. "Anyway, re-add Tiefkühl and tell me to just check what they have there as TK-Gemüse, and a note at the end that I should go to EDEKA someday this or next week"

qwertox commented on MapLibre Tile: A next generation geospatial format optimized for rendering   arxiv.org/abs/2508.10791... · Posted by u/mtremmel
ajd555 · 4 days ago
This is such great news, and these are very notable speedups (decoding and filtering)! I'm looking to host our own tiles, and this would not only reduce file size but also improve performance on our maps (https://dash.hudsonshipping.co could use a speedup in loading the tiles, though we are ever grateful to OpenFreeMap). Will keep an eye out for MapLibre news regarding the JS release of this.
qwertox · 4 days ago
I can't see the map. It does not display neither on Firefox nor on Chrome, even with uBlock Origin disabled. Console shows "08:27:58.824 Uncaught TypeError: can't access property "Speed", hourlySpeeds[157] is undefined"

u/qwertox

KarmaCake day9460December 17, 2017View Original