That's exactly what we want, a lamp that's just as annoying as an orange cat. /s
Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
101–110 of 110 posts
Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#102Just waiting for the azathoth version
Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#103Earlier quoted context omitted.
https://ppubs.uspto.gov/pubwebapp/static/pages/ppubsbasic.ht... Have a look. For instance in the search box enter "categories".
> Search results > Results for query "(Categories).pn." > No records found
I am sorry for not being precise. You should enter "Categories" in "For" input. (in the "Or" section)
Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#104Earlier quoted context omitted.
I wondered similar. Perhaps a local model cached in a 16GB or 24GB graphics card would perform well too. It would have to be a quantized/distilled model, but maybe sufficient, especially with some additional training as you mentioned.
If Qwen 0.6B is suitable, then it could fit in 576MB of VRAM[0]. https://huggingface.co/unsloth/Qwen3-0.6B-unsloth-bnb-4bit
or on a single Axera AX630C module: https://www.youtube.com/watch?v=cMF6OfktIGg&t=25s
Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#105Earlier quoted context omitted.
This feels similar to not finding a game fun once I understand the underly system that generates it. The magic is lessened (even if applying simple rules can generate complex outcomes, it feels determined)
My gripe with all procedural generated content in games, like e.g. Starbound. There's a tiny state space inflated via RNG, and it takes me just moments to map out the underlying canonical states and lack of any correlation between properties of an instance, or between them and the game world. The moment that happens, the game loses most of its fun, as I can't help but perceive the poor base wearing random cosmetics.
procedural generation can produce infinite variety but it cannot produce infinite novelty.
Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#106Earlier quoted context omitted.
My gripe with all procedural generated content in games, like e.g. Starbound. There's a tiny state space inflated via RNG, and it takes me just moments to map out the underlying canonical states and lack of any correlation between properties of an instance, or between them and the game world. The moment that happens, the game loses most of its fun, as I can't help but perceive the poor base wearing random cosmetics.
procedural generation can produce infinite variety but it cannot produce infinite novelty.
Right. However, we don't need infinite variety, or even much variety at all, if that variety makes sense, if it fits the game world and experience in some way. Pure randomness is boring and easy to dismiss wholesale once you realize there's no meaning behind it.
Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#107Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#108Earlier quoted context omitted.
Furbies spring to mind... They were a similar shape and size and even had two goggling eyes, but with waggling ears instead of a tentacle. They'd impress you initially but after some experimentation you'd realize they had a basic set of behaviors that were triggered off a combination of simple external stimuli and internal state. (this is the part where somebody stumbles in to say "dOn'T hUmAnS dO ThE sAmE tHiNg????"…
> (this is the part where somebody stumbles in to say "dOn'T hUmAnS dO ThE sAmE tHiNg????") As a frequent "your stated reasoning for why llms can't/don't/will-never applies to humans because they do the same thing" annoying commentor, I usually invoke it to point out that a) the differences are ones of degree/magnitude rather than ones of category (i.e. is still likely to be improved by scaling, even if there are dim…
I disagree with your response, because you are confusing the difference between modeling human behavior and being human.
According to you a video of a human and a human are the same thing. The video is just as intelligent and alive as the human. The differences are merely one of degree or magnitude rather than ones of category. Maybe one video isn't enough, but surely as we scale the database towards an infinite amount of videos, the approximation error will vanish.
Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#109I e been wanting to do this with a basic stuffed animal now for a while. Just basic interactions with a child plus lessons and a voice would be game changing for the toy world.
> "Teddy," he said, "I'm going to pull up flowers from the flower bed.” "No Davy . . . pulling up flowers is naughty . . . don't pull up the flowers.” The little voice squeaked and the arms waved.
> "Teddy, I'm going to break a window.” "No, Davy . . . breaking windows is naughty . . . don't break any windows . . .” "Teddy, I'm going to kill a man.” Silence, just silence. Even the eyes and the arms were still.
> The roar of the gun broke the silence and blew a ruin of gears, wires and bent metal from the back of the destroyed teddy bear.
> "Teddy . . . oh, teddy . . . you should have told me," David said and dropped the gun and at last was crying.
Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL
#110Earlier quoted context omitted.
> (this is the part where somebody stumbles in to say "dOn'T hUmAnS dO ThE sAmE tHiNg????") As a frequent "your stated reasoning for why llms can't/don't/will-never applies to humans because they do the same thing" annoying commentor, I usually invoke it to point out that a) the differences are ones of degree/magnitude rather than ones of category (i.e. is still likely to be improved by scaling, even if there are dim…
I disagree with your response, because you are confusing the difference between modeling human behavior and being human. According to you a video of a human and a human are the same thing. The video is just as intelligent and alive as the human. The differences are merely one of degree or magnitude rather than ones of category. Maybe one video isn't enough, but surely as we scale the database towards an infinite amou…
C'est ne pas une pipe, the map is not the territory, sure.
But I disagree that my argument doesn't hold here - if I re-watch a Hank Green video, I can perfectly model it because I've already seen it. This reveals the video is not alive. But if I watch Hank Green's whole channel, and watch Hank's videos every week, I can clearly tell that the entity the video is showing, Hank Green the Human, is alive.