News for hackers. Stuff that matters.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by XCSme on Monday August 17, 2026 @02:58AM (#49327331)
My comparison of its reasoning efforts[0] seems to show that it only really supports 3 modes: none, low, xhigh.

Low and medium are basically the same.

Also, the electricity it costs to run on a 3090 is not negligible, so that it's cheaper to use Luna high via API than Qwen 3.8 27b locally, hardware costs excluding.

[0]: https://aibenchy.com/compare/qwen-qwen3-8-27b-high/qwen-qwen...

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by monster_truck on Monday August 17, 2026 @03:09AM (#49327388)
$0.286/kWh is a ridiculous amount of money to pay for power. That's more than double the regional residental average here!

If I ever found myself in this situation I would much rather just rent cards from hotasile and run open models instead of giving OAI money and playing reset bingo

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by AgentMatt on Monday August 17, 2026 @03:18AM (#49327434)
Ridiculous? Wow. I'm paying ~$0.4/kWh in western Europe...
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by sgt on Monday August 17, 2026 @03:59AM (#49327697)
Paying around ~$0.25-0.3 per kWh here in South Africa. But you can also put up a lot of solar panels and lower that effectively.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by a96 on Wednesday August 19, 2026 @04:32AM (#49358705)
Wow. Those are about EV quick charge prices here in .fi. Average residential is maybe 0.06 €/kWh (plus transfer and subscription).

<https://sahkovertaaja.fi/porssisahkon-keskihinta/>

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by theshrike79 on Monday August 17, 2026 @03:26AM (#49327477)
The current spot price in northern Europe is 0.025€/kWh, yesterday it was 0.007€/kWh :D
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by XCSme on Monday August 17, 2026 @03:12AM (#49327411)
I removed the extra links to sources for the electricity prices, but that's the average cost in EU, where I live.

https://ec.europa.eu/eurostat/web/products-eurostat-news/w/d...

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by SimplyUnknown on Monday August 17, 2026 @03:26AM (#49327475)
Indeed, EPEX spot prices are between €0.30 and €0.39 today including taxes where I live. I've seen them go up to €1.10 during peak demand.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by hokkos on Monday August 17, 2026 @05:42AM (#49328458)
it is not the marginal price for household users, but the (average electricity bill : subscription + consumption) / (average consumption), so it will be higher than the additional kwh consumed.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by XCSme on Monday August 17, 2026 @05:47AM (#49328502)
Maybe, but only it's marginally off.

This is what I pay extra per kWh,in Netherlands: € 0,25162 ($0.291), excluding the connection costs.

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by XCSme on Monday August 17, 2026 @03:14AM (#49327413)
Also, note that the Luna was run and costs were calculated through OpenRouter, via API. With a ChatGPT subscription it's likely even cheaper.

Also, Qwen 3.7 27B is actually Terra level.

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by sunaookami on Monday August 17, 2026 @03:17AM (#49327430)
Welcome to Europe
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by m1keil on Monday August 17, 2026 @07:42AM (#49329327)
Can be easily the price you will pay across Australia, depending on the time of day.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by ThrowawayTestr on Monday August 17, 2026 @02:13PM (#49335254)
We're privileged in North America to have cheap power.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by sgt on Monday August 17, 2026 @04:02AM (#49327718)
Btw, unrelated, but this is the kind of Vibe Coded AI slop design I see a lot these days. Every single thing on this page has a different color, formatting, and it's just painful to look at.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by XCSme on Monday August 17, 2026 @05:34AM (#49328396)
Thanks for the feedback!

That might be my fault, I am not a designer, and I asked for most UI decisions.

I tried to use colors to diferentiate models, the site is very data dense and it's hard to make everything readable.

I've spent hundreds of hours building it, not sure if I would call it slop, but I just suck at design, lol

Any suggestions on how to improve it?

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by sgt on Monday August 17, 2026 @06:26AM (#49328774)
How about a complete rewrite that is not vibe coded? I'm only half serious. You're likely to use an LLM to help develop it, but don't let it take you for a ride. LLM's really struggle with data dense and robust designs.

Have a look at https://diskprices.com/ - this is great UX because it's extremely functional, yet it has nearly no design to speak of. On a scale of data dense designs, this one would be on the extreme side, so I guess if you ask the LLM to meet you somewhere in the middle.

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by XCSme on Monday August 17, 2026 @06:36AM (#49328839)
I am still pretty happy with some UX decisions I took:

- the spotlight search, you can do ctrl+k and search "gpt vs claude vs google" and it automatically shows the most relevant comparison

- drag to reorder compared models

- filter leaderboard by multiple comma separated needles, so you can see for example all qwen and kimi models only

- the showcases page is quite cool

A lot of invisible UI/UX features are there, which I think work great, only the visual presentation could be, as you mentioned, a lot better.

Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by sgt on Monday August 17, 2026 @08:34AM (#49329838)
Fair enough. I'll check it out in the next few weeks to see how the site evolves.
Re:Qwen 3.8 27B is excellent, but it defaults to overthinkin... by XCSme on Monday August 17, 2026 @06:32AM (#49328816)
I do try to guide it, I don't think strictly telling LLMs what to do works best. I like letting the LLM do what it thinks it's best (supposedly it is a lot smarter than me), and then guide it in the directions I think it should go and fix the flaws I notice.

I checked out that link on mobile, but it's unfortunately unusable. I will check it out later on desktop, thank you.