I wonder how far this can be taken. Could Qwen 3.8 can interpret and make improvements to Qwen 3.5 0.8B weights, or even its own weights?

▲

stymaar 3 hours ago | parent | next [-]

I wouldn't be surprised at all if 3.8-27B could tweak 3.5-0.8B the same way Astra did, but it wouldn't be a big deal either because that part of the paper has nothing to do with directly tweaking the weights like the first part of the paper, but is instead a fairly straightforward abliteration method on a model that is known for a specific pathological behavior (ending up stuck in a thinking loop).

	▲	solnyshok 3 hours ago \| parent [-]
		isn't consciousness just that, a thinking loop with interruptions for sleep until we break beyond repair? and, just maybe, if we managed to figure out the meaning of life, our thinking would satisfyingly stop?

▲

f311a 3 hours ago | parent | prev | next [-]

It can, as long as you can give it benchmarks. What it can't do is optimize general intelligence without any external validation.

You can optimize a model by randomly changing its weights and validating results on your task. A monkey can type a book given enough attempts.

▲

latentsea 3 hours ago | parent | prev | next [-]

What I want to see someone try and succeed at would be to get the really highly quantized models to loop less. Many people with only 16GB VRAM are running the IQ3_XXS or IQ3_S quants of Qwen3.8-27B. If it could figure out how to improve those quants, that'd actually be pretty substantial. That's all they did for those improved math results is removed the looping. Why not? Please someone. Please.

	▲	rhdunn 2 hours ago \| parent [-]
		It's fairly straightforward to write a function that detects looping output -- I wrote one for promptfoo in [1]. For training you would need to hook it up to a LoRA training harness, identify the looping weight direction, and adjust the weights accordingly. I've not (yet) looked into how to do this. [1] https://news.ycombinator.com/item?id=48555634

▲

awb 3 hours ago | parent | prev | next [-]

Is RSI here? No.

▲

TMWNN 2 hours ago | parent | prev | next [-]

https://upload.wikimedia.org/wikipedia/en/b/ba/DrawingHands....

▲

m3kw9 2 hours ago | parent | prev [-]

i feel like this could turn out to be a over unity demo where they say the model can improve a model better than it's own. (more energy output than input)