Yeah I'm just beginning my local AI journey on a 5080, tried Qwen3.6 27b Q4 and was getting like 1tps because of the vram overflow. Ran it over night at it was still chewing on generating a prompt for a sub agent when I got up in the middle of the night until it simply ended in some kind of "fetch failure" lol. I think I gave it something too large to tackle, but either way 1tps is kinda garbage.

Assuming the vars are all really short, it sounds like the same idea behind Webpack's (et al) minification & mangling to achieve tiny performance gains everywhere it can. Which might mean there's a dev version that isn't squashed and ugly, but doesn't make it to us..?

But that context is a mix of model output and other sources. The model output portion was generated token by token, and is combined in interesting ways with things like human response, search results, software output. It's still a backward looking mechanism, rather than having established a concept as a goal and then trying to build the words to reach that concept like we do.

Size and strategy for managing the context has been critical for improved subjective results, but it still doesn't exhibit the behavior of the words as a tool to address some concept, everything about the model is about the words themselves. So we end up with something very good at generating what seems right and there's a super high chance of what seems to be right actually being right. Especially when the software can automatically execute commands and the good or bad results reach into the context window, enabling it to effectively get automatically second guessed. The potential for automatic verification in some scenarios automatically feeding the context window is what makes it particularly appealing for software folks, though not universal.

Well that description of a car is actually fairly close to the fundamentals, add an engine or motor and a steering wheel, and you've got it. Yes, a lot of engineering goes into the best possible realization of those basics, efficiency, suspension, safety, maintenance, and just a ton of more stuff, and it is a very valued execution above and beyond what, say, the Model T delivered. Automotive engineers have done hard and valuable work and complicated work, but no one is surprised that Model T led to faster, more comfortable, safer, more convenient vehicles that move around. It is a bit more surprising that LLM architecture works as well as it does while always focusing on the next token without ability to go further, best case running through and messing up and regenerating until you have operator appropriate output.

The 'seahorse emoji' was a pretty fun example of this at work, as it didn't have a seahorse emoji, but since it wasn't trying to generate the emoji, it started by building up the words to confirm and introduce the emoji since obviously there will be one, then putting up a wrong thing, then the words that would go after the wrong thing, but the weight still suggested there should be a correct answer and to start generating words for another try, and so on. "Reasoning" does the job of incurring this hit out of sight a lot of the time. Looking at the reasoning chains you'll see this behavior a fair amount, that the model suggests words that build toward an answer but fails on the key word and retries until something tests right or it models that it tried enough and it can't find the key word that would have been expected. It can of course digest it's own output and summarize the result without showing the operator spinning out, but it at all times is operating on the fundamental principle of model+very cleverly managed context influencing an answer one token at a time and ideally discarding the first run.

I assumed that but everything I have seen as I dug deeper has been that at some level that is what is happening. If it is 'reasoning', it's generating a 'reasoning chain' next token by next token and using that to influence the final output tokens. The reasoning chain is discarded and since the actual output is a continuation of the reasoning chain it may conceptually be described as allowing the model to 'rethink' things, but even as the generation of a 'reasoning chain' has results that more closely resemble reasoning, it is still a scenario where it's building it one token at a time and we get to see meaning as an emergent property, rather than trying to find words to build to a more abstract concept like humans do. It just gets to throw away the intermediate work and the extra tokens manage to improve the 'accuracy' of the preserved final output.

Its just a ball rolling down a hill trying to find the lowest point, but its like a super fancy ball with a ton of rules, and the hills are really detailed with like little walls and bridges and stuff.

Ppl who think in abstracts, ppl who can't visualize, people who have no inner dialouge, etc. fat variety

That conclusion requires a combination of empathy and compassion, characteristics people who become CEOs who rarely have.

The ones that do often get outmaneuvered by their peers and get kicked out.

If I had their money, I would just study every subject, using every coach, until I physically can't learn more.

AFAIK, their open models are distributed as weights, not executables and are therefore not able to start network connections / run code. There is of course tool-calling functionality but that just works by having the model output a special pattern and having something external run predetermined commands based on that.

They are open source models, nothing malicious about them. I'd be much more careful about where you run your agents on. The wrong prompt can even make a non-malicious model misbehave.

The beauty of it is that it doesn't need tracker shit. It works to destroy the US AI bubble even without anything malicious within.

And considering how hard the US researchers have been trying to control the output of their general LLMs, with little success, why would the Chinese have found a way before everyone else even thinks it's possible?

I was suprised when chatgpt used ffmpeg and yt-dlp to check a frame of a video idk if it actually suceeded or lied

Hire some already underpaid VFX artists

Is there a petition?

https://www.tomshardware.com/software/search-engines/archive-today-allegedly-leads-bizarre-ddos-campaign-against-security-blogger-wikipedia-considers-removing-all-links-to-the-archive