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

91–100 of 110 posts

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

#91

Post by phh »

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…

Kyutai's unmute has great latency, but requires a fast small-ish, non-thinking, non-tooled LLM. What I'm currently working on is merging both worlds. Take the small LLM for instant response, which will basically just be able to repeat what you said, to show it understood. And have a big LLM do stuff in the background, and feeding back infos to the small LLM to explain intermediary steps.

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

#92

Post by rixed »

Sharlin wrote: post #37
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…

People have always been ascribing agency and sapience to things, from fire and flowing water in shamanistic religions, to early automatons that astonished people in the 18th century, to the original rudimentary chatbots, to ChatGPT, to – more or less literally – many other machines that may seem to have a "temperament" at times.

Friendly reminder that "seem to have a temperament", aka "this funny thing looks like something complex is going on under the surface", is the only basis we have to ascribe agency and sapience to any human being, starting from outselves.

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

#93

Post by endymion-light »

phh wrote: post #91
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…

Kyutai's unmute has great latency, but requires a fast small-ish, non-thinking, non-tooled LLM. What I'm currently working on is merging both worlds. Take the small LLM for instant response, which will basically just be able to repeat what you said, to show it understood. And have a big LLM do stuff in the background, and feeding back infos to the small LLM to explain intermediary steps.

This is the key aspect for future development of models - small instant reasoning, ideally on device that funnels through tho a larger model for reasoning.

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

#95

Post by antonvs »

LordDragonfang wrote: post #70
floren wrote: post #32

Earlier 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…

> the poster is unconsciously arguing from a place of human exceptionalism

I find the specifics of that exceptionalism interesting: there's typically a lack of recognition of their own thinking process as having an explanation.

Human thought is assumed to be a mystical and fundamentally irreproducible phenomenon, so anything that resembles it must be "just" prediction or "just" pattern matching.

It's quite close to belief in a soul as something other than an emergent phenomenon.

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

#96

Post by varispeed »

dotancohen wrote: post #86
varispeed wrote: post #9

Earlier quoted context omitted.

This always grinds my gears. For some people "discoveries" are so obvious, they don't bother writing a paper let alone patenting it. Then someone goes and patents it...

Examples?

https://ppubs.uspto.gov/pubwebapp/static/pages/ppubsbasic.ht...

Have a look. For instance in the search box enter "categories".

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

#97

Post by dotancohen »

varispeed wrote: post #96
dotancohen wrote: post #86

Earlier quoted context omitted.

Examples?

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

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

#98

Post by bambax »

floren wrote: post #32
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…

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????"…

But... dOn'T hUmAnS dO ThE sAmE tHiNg????
Post reply on HN