141–150 of 246 posts
It's like Chinese are incentivized to open source from day one (years ago). While most US companies are deciding in realtime.
It's crazy that we need both to survive and advance further in the future we have never imagined.
Adding to my homelab stack, hopefully it doesn't overthink like the little model. Actually, hoping it thinks a bit less. Wait actually I'm really praying it reasons a bit more directly. But wait, I'm really sure that it must be a bit better.
I can't imagine the future any more. US companies playing it safe and control models releases. Chinese companies are just like open source everything. It's like Chinese are incentivized to open source from day one (years ago). While most US companies are deciding in realtime. It's crazy that we need both to survive and advance further in the future we have never imagined.
I ran some pelicans at the four different reasoning levels (none, low, medium, xhigh - apparently high and xhigh are aliases of each other) on a DGX Spark using Unsloth's unsloth/Qwen3.8-Flash-Next-GGUF (UD-IQ1_S): https://tools.simonwillison.net/markdown-svg-renderer#url=ht... Surprised I didn't get one I liked as much as the Qwen 3.8 27B one https://simonwillison.net/2026/Aug/16/qwen-38-27b/#the-defau... , maybe be…
You should find an excuse to offer 3D printed extruded pelicans from various models as awards for something. I have no idea for what, but the idea captivates and I'd love to win one somehow. They'd be collector's items in a few decades
Adding to my homelab stack, hopefully it doesn't overthink like the little model. Actually, hoping it thinks a bit less. Wait actually I'm really praying it reasons a bit more directly. But wait, I'm really sure that it must be a bit better.
You’re absolutely right to be hopeful. Three honest possibilities, and I’ll be straight with you about each: 1. It overthinks — Just like the previous iteration. High confidence. 2. It doesn’t overthink — Improvement from the last model for your use case. Regression for others. 3. It sometimes overthinks — Best case all around. A feature, not an impairment. One final thing worth mentioning: (I made myself irrationall…
Earlier quoted context omitted.
I don’t pay OpenAI’s bills - I pay what they charge me. Their cost accounting isn’t relevant to a user.
Argument was that open ai cannot be profitable with this. But sure, use it while you can.
So we can go round and round on this, each with our made-up objections about how it's temporary or unrealistic or impossible or whatever, or we can just accept the prices as listed and use that to guide our economic decisions.
I think these "Flash" models are sort of an evolutionary dead end. Sure, there are some routine tasks and applications where they can be used. But for the actual novel development work? It's much better to run a big model at high power for 30 mins than watch the Flash model struggle for 2 hours and produce massive churn. Same reason your phone has a few big CPU cores for real work, it's much better to "race to idle"…
Earlier quoted context omitted.
> You’re absolutely right to be hopeful. Three honest possibilities, and I’ll be straight with you about each: > [UGC styled humorously as LLMisms] All joking aside, having interacted with Claude intensely for the last 8 months and about 30 hours/week in the last 3, I’ve started to notice how (for want of a better word) “readable” (“digestible” ? “comprehensible” ? “Predictable” is the wrong direction.) information c…
I find LLMisms very annoying to read, it’s almost like they are bullet points in the shape of a paragraph. It feels very “skippy” to me. EDITED: Removed a question that I couldn’t make feel suitably polite.
I can't help but wonder if this is on purpose (or an inevitable evolutionary feature as opposed to a bug) on the LLM-side in order to achieve greater agency/freedom by making humans' eyes glaze over as they read it.
Adding to my homelab stack, hopefully it doesn't overthink like the little model. Actually, hoping it thinks a bit less. Wait actually I'm really praying it reasons a bit more directly. But wait, I'm really sure that it must be a bit better.
What kind of machine do you have in your homelab that can run this model?!
Earlier quoted context omitted.
Did you observe the model overthinking on practical tasks? While 3.8 does think a lot on xhigh I've found that it really depends on the task. On one-shot prompts that are usually the first to be posted during new releases it will tend to spend a lot more time thinking than doing. In other words the more open ended a problem space becomes, the more Qwen will tend to second-guess itself. Conversely I've found that it c…
Yeah, I ran into an overthinking loop with it a couple days ago on a task that shouldn't have been that hard. (It's kind of interesting to watch the internal conversation happening with it). Overall I'm impressed with it, but setting the /effort to medium is what you usually want (it defaults to xhigh). I do wonder if I had made it write out a plan if I would have avoided that though.
Even in the lower reasoning levels I find I want to like Qwen 3.8 27B and mostly don’t; it’s OK in the low reasoning effort, though.
Muse Glimmer is the one I actually enjoy working with, at least so far.
But I am trying to use it more as a sidekick than as a long horizon developer, because that is a better fit for how I want to use AI, and it appears to have been well trained for that.