Viewing profile — XCSme

As a solo dev, this gives me hope. I feel like I have an advantage over big companies, if I can use the best models on a subscription and not worry about costs much, when they can'…

My question was more about more complex problems, which no seem to be multi-turn somehow, or maybe just the harnesses make it look that way. I am curious what the drop in thoughput…

Yeah, makes sense, if it's good for very small models only, then there's no point, as those van already run on cheap consumer hardware. Yet, maybe it can work well enough, so that …

I asked a LLM after posting my comment, to see if I had a genius idea or not,just for it to tell me the same as you, that's now they work already...

My concern is that reasoning could involve some sequential steps that instant models don't. Not sure if modern models "think" only by outputting blocks, or there is a more complex …

It was just a random example, you could think of it as being a lot more complex (detect which type of food it is, what detergent to use, how much water, remember patterns, learn ov…

So local personalized ads? Not sure if that's better or worse than online personalizaed ads...

Why not have some a device/hardware that programs itself on-boot. Sort of a FPGA, that (electrically) arranges the connections on-boot, and then it's like a static inference chip.

I think this would make sense for consumer hardware, not for AI companies. AI companies constantly update/change stuff, new models come out, new requirements, etc. But if you ship …

Wait, is it even thinking? Or is it an instant model?

Wow, that's instant, crazy.

I am surprised that they keep going with it, seeing how fast it improves and basically soon running themselves too out of business. What's even their end goal? Open source models m…

If they trained it well, and can do computer use, it will be a new era. Companies can keep PCs, put Qwen 3.8 27b on it and get rid of the employees, lol...

Can't really use it now, without giving away your data: > Trains: this provider may use prompts for training and may retain prompt data.

Or maybe not: https://news.ycombinator.com/item?id=49119559

I think that with this change, DeepSeek v4 Flash has finally been dethroned.

Wasn't one of the main original points of LLMs to be creative? To create stories, creative writing?

Is this like Runescape free armour trimming? You send your gpu, and get it back with 2x memory?

Depends on whether the models report the correct amount of tokens. 5.5 Sol repors 10x fewer reasoning tokens than Kimi k3. If it is correct, than it unlikely has those doubt issues…

Yeah, they thing forever and doubt everything "wait but" for 200k tokens for almost any question.

So nowadays the hardware and hosting providers must be in an optimization race, whoever can make the model just a bit smaller or more efficient (to fit on fewer/less powerful cards…

One of the best hamsters [0]. Again, their "none" version costs more than "low", and says zero reasoning tokens, makes no sense[1]. As always, the "low" version seems to be the bes…

Twice the cost for 4% more intelligence, is it worth it?

I have a spare 3090 that I want to use to off-load some tasks from Claude to a local model (probably Qwen 3.6 27b), any success with that? Is it good enough to follow some tasks, c…

I thought login-protected apps are not allowed on Show HN.