Qwen 3.8 27B is excellent, but it defaults to overthinking things

Post by mattmaroon » Mon, Aug 17, 2026, 7:10 AM UTC

redrove wrote: post #145

mattmaroon wrote: post #133

Earlier quoted context omitted.

Yes. Bureaucracy for sure when I throw festivals. ChatGPT pulls permits for me. (I think that uses a lot of tokens because of the browser control?) Manages the admin side along with some tools I built in Lovable via mcp servers. Marketing definitely. My food truck side is relatively high volume and it manages my kitchen and warehouse side, basically generating all of the instructions my employees follow, managing and…

Thanks for the very detailed answer! Would you say ChatGPT does everything you need today or do you still see some gaps? i.e. things you think it should be able to do but currently doesn’t, or things that still take too much effort on your part to setup chatgpt to do it.

Post by qeternity » Mon, Aug 17, 2026, 7:11 AM UTC

chaboud wrote: post #82

cchance wrote: post #74

Earlier quoted context omitted.

All these weird partial language thought patterns im surprised none of the teams have taught the models to think in something like court stenography or some very dense pattern (i mean they even tried caveman language at one point)

Keep in mind that the model is thinking in a token space, itself a compressive representation of language. (Note: there's still a huge grammar penalty, so, ugh do think small.)

Post by XCSme » Mon, Aug 17, 2026, 7:14 AM UTC

monster_truck wrote: post #150

XCSme wrote: post #142

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...

$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

Post by sunaookami » Mon, Aug 17, 2026, 7:17 AM UTC

monster_truck wrote: post #150

XCSme wrote: post #142

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...

$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

Post by janalsncm » Mon, Aug 17, 2026, 7:24 AM UTC

fweimer wrote: post #135

refactor_master wrote: post #33

Earlier quoted context omitted.

Unlike cloud infra in general which offers things like automatic backups, regional redundancy, and effectively unlimited scalability, it seems like the value proposition of cloud LLM gets ever shakier. * Many businesses don't need frontier level intelligence anyway. * It's completely stateless. If your local LLM machine catches fire? Nothing was lost. Buy another.

Centralized inference can easily increase batch size, leading to huge efficiency gains in the usual scenario where most users have just one or very few session. Using local resources efficiently requires some way to increase the batch size. I'm not sure if we are there yet.