Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

matthieulc.com

Post reply on HN
Print view View original

21–30 of 110 posts

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#21

Post by accrual »

dylan604 wrote: post #18

"ah, you hesitated" no more so than on every single other question. the delay for the GPT to process a response is very unnerving. I find it worse than when the news is interviewing a remote site with a delay between responses. maybe if the eyes had LEDs to indicate activity rather than it just sitting there??? waiting for a GPT to do its thing is always going to force a delay especially when pushing the request to t…

> also, "GPT-4o continuously listens to speech through the audio stream," is going to be problematic

This seems like a good place to leverage a wake word library, perhaps openWakeWord or porcupine. Then the user could wake the device before sending the prompt off to an endpoint.

It could even have a resting or snoozing animation, then have it perk up when the wake word triggers. Eerie to view, I'm sure...

https://github.com/dscripka/openWakeWord

https://github.com/Picovoice/porcupine

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#22

Post by jszymborski »

dylan604 wrote: post #18

"ah, you hesitated" no more so than on every single other question. the delay for the GPT to process a response is very unnerving. I find it worse than when the news is interviewing a remote site with a delay between responses. maybe if the eyes had LEDs to indicate activity rather than it just sitting there??? waiting for a GPT to do its thing is always going to force a delay especially when pushing the request to t…

I wonder how well suited some of the smaller LLMs like Qwen 0.6B would be suited to this... it doesn't sound like a super complicated task.

I also feel like you can train a model on this task by using the zero-shot performance of larger models to create a dataset, making something very zippy.

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#23

Post by jameshart »

blamestross wrote: post #8
lukeinator42 wrote: post #7

Earlier quoted context omitted.

If it's described in a paper doesn't that make it prior art though?

Not if it is the authors of the paper filing for the patent. Otherwise people would never publish papers.

Patents are intended to be the form of first public disclosure of an idea. Disclosing it before patenting it can prevent the patent application being valid.

US has a 1 year grace period. In most countries, any public disclosure makes an idea unpatentable.

https://outlierpatentattorneys.com/patent-public-disclosure

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#24

Post by accrual »

jszymborski wrote: post #22
dylan604 wrote: post #18

"ah, you hesitated" no more so than on every single other question. the delay for the GPT to process a response is very unnerving. I find it worse than when the news is interviewing a remote site with a delay between responses. maybe if the eyes had LEDs to indicate activity rather than it just sitting there??? waiting for a GPT to do its thing is always going to force a delay especially when pushing the request to t…

I wonder how well suited some of the smaller LLMs like Qwen 0.6B would be suited to this... it doesn't sound like a super complicated task. I also feel like you can train a model on this task by using the zero-shot performance of larger models to create a dataset, making something very zippy.

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.

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#25

Post by accrual »

huevosabio wrote: post #13

This is so cool! I love the idea of adding expressivity to non verbal, non human entities.

Agreed! I think the Pixar lamp is a great starting point. Having the robot be able to flex and bend, shake yes/no, look curious or upset, and perhaps even let it control LEDs to express itself.

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#26

Post by jszymborski »

accrual wrote: post #24
jszymborski wrote: post #22

Earlier quoted context omitted.

I wonder how well suited some of the smaller LLMs like Qwen 0.6B would be suited to this... it doesn't sound like a super complicated task. I also feel like you can train a model on this task by using the zero-shot performance of larger models to create a dataset, making something very zippy.

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

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#27

Post by dylan604 »

ceejayoz wrote: post #14
sparrish wrote: post #2

Hell no! I seen this movie and I don't want any face-hugger sitting on my desk.

Hentai enthusiasts, on the other hand...

Hey, what are you watching?

I swear it's work related. You should see the other training data I had to use

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#28

Post by justusthane »

dylan604 wrote: post #18

"ah, you hesitated" no more so than on every single other question. the delay for the GPT to process a response is very unnerving. I find it worse than when the news is interviewing a remote site with a delay between responses. maybe if the eyes had LEDs to indicate activity rather than it just sitting there??? waiting for a GPT to do its thing is always going to force a delay especially when pushing the request to t…

> the delay for the GPT to process a response is very unnerving

I'm not sure I agree. The way the tentacle stops moving and shoots upright when you start talking to it gives me the intuitive impression that it's paying attention and thinking. Pretty cute!

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#29

Post by zhyder »

Beautiful work! I appreciate how this robot clearly does NOT try to look like any natural creature. I don't want a future where we can't easily distinguish nature from robotics. So far humanoid robots look clearly robotic too: hope that trend continues.

Re: Show HN: Shoggoth Mini – A soft tentacle robot powered by GPT-4o and RL

#30

Post by anotherjesse »

rainingmonkey wrote: post #15

What a fascinating intersection of technology and human psychology! "One thing I noticed toward the end is that, even though the robot remained expressive, it started feeling less alive. Early on, its motions surprised me: I had to interpret them, infer intent. But as I internalized how it worked, the prediction error faded Expressiveness is about communicating internal state. But perceived aliveness depends on somet…

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)
Post reply on HN